· Trending Papers
Emergent Mind

A Comprehensive Survey of Continual Learning: Theory, Method and Application

(2302.00487)
Published Jan 31, 2023 in cs.LG , cs.AI , and cs.CV

Abstract

To cope with real-world dynamics, an intelligent system needs to incrementally acquire, update, accumulate, and exploit knowledge throughout its lifetime. This ability, known as continual learning, provides a foundation for AI systems to develop themselves adaptively. In a general sense, continual learning is explicitly limited by catastrophic forgetting, where learning a new task usually results in a dramatic performance degradation of the old tasks. Beyond this, increasingly numerous advances have emerged in recent years that largely extend the understanding and application of continual learning. The growing and widespread interest in this direction demonstrates its realistic significance as well as complexity. In this work, we present a comprehensive survey of continual learning, seeking to bridge the basic settings, theoretical foundations, representative methods, and practical applications. Based on existing theoretical and empirical results, we summarize the general objectives of continual learning as ensuring a proper stability-plasticity trade-off and an adequate intra/inter-task generalizability in the context of resource efficiency. Then we provide a state-of-the-art and elaborated taxonomy, extensively analyzing how representative methods address continual learning, and how they are adapted to particular challenges in realistic applications. Through an in-depth discussion of promising directions, we believe that such a holistic perspective can greatly facilitate subsequent exploration in this field and beyond.

We're not able to analyze this paper right now due to high demand.

Please check back later (sorry!).

Generate a detailed summary of this paper with a premium account.

We ran into a problem analyzing this paper.

Subscribe by Email

Get summaries of trending comp sci papers delivered straight to your inbox:

Unsubscribe anytime.

YouTube
References
  1. Conditional channel gated networks for task-aware continual learning. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 3931–3940
  2. Iirc: Incremental implicitly-refined classification. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 11038–11047
  3. Wickliffe C Abraham. Metaplasticity: tuning synapses and networks for plasticity. Nature Reviews Neuroscience, 9(5):387–387
  4. Metaplasticity: the plasticity of synaptic plasticity. Trends in Neurosciences, 19(4):126–130
  5. Life-long disentangled representation learning with cross-domain latent homologies. Advances in Neural Information Processing Systems, 31
  6. Gp-tree: A gaussian process classifier for few-shot incremental learning. In International Conference on Machine Learning, pages 54–65. PMLR
  7. Continual learning with adaptive weights (claw). In International Conference on Learning Representations
  8. Semantics-driven generative replay for few-shot class incremental learning. In Proceedings of the ACM International Conference on Multimedia, pages 5246–5254
  9. Uncertainty-based continual learning with adaptive regularization. Advances in Neural Information Processing Systems, 32
  10. Ss-il: Separated softmax for incremental learning. In Proceedings of the IEEE/CVF International Conference on Computer Vision, pages 844–853
  11. Subspace regularizers for few-shot class incremental learning. In International Conference on Learning Representations
  12. Memory aware synapses: Learning what (not) to forget. In Proceedings of the European Conference on Computer Vision, pages 139–154
  13. Online continual learning with maximal interfered retrieval. In H. Wallach, H. Larochelle, A. Beygelzimer, F. d'Alché-Buc, E. Fox, and R. Garnett, editors, Advances in Neural Information Processing Systems, pages 11849–11860. Curran Associates, Inc.
  14. Expert gate: Lifelong learning with a network of experts. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pages 3366–3375
  15. Task-free continual learning. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 11254–11263
  16. Gradient based sample selection for online continual learning. Advances in Neural Information Processing Systems, 32
  17. Learning fast, learning slow: A general continual learning method based on complementary learning system. In International Conference on Learning Representations
  18. Varigrow: Variational architecture growing for task-agnostic continual learning based on bayesian novelty. In International Conference on Machine Learning, pages 865–877. PMLR
  19. Activity-dependent gating of lateral inhibition in the mouse olfactory bulb. Nature Neuroscience, 11(1):80–87
  20. A closer look at memorization in deep networks. In International Conference on Machine Learning, pages 233–242. PMLR
  21. Class-incremental learning with cross-space clustering and controlled transfer. In European Conference on Computer Vision, pages 105–122. Springer
  22. Dopaminergic neurons write and update memories with cell-type-specific rules. Elife, 5:e16135
  23. Mushroom body output neurons encode valence and guide memory-based action selection in drosophila. Elife, 3:e04580
  24. Few-Shot Continual Active Learning by a Robot
  25. Eec: Learning to encode and regenerate images for continual learning. In International Conference on Learning Representations
  26. Structural components of synaptic plasticity and memory consolidation. Cold Spring Harbor Perspectives in Biology, 7(7):a021758
  27. Rainbow memory: Continual learning with a memory of diverse samples. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 8218–8227
  28. Online continual learning on a contaminated data stream with blurry task boundaries. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 9275–9284
  29. Analytic-dpm: an analytic estimate of the optimal reverse variance in diffusion probabilistic models. In International Conference on Learning Representations
  30. Learning to continually learn. In ECAI 2020, pages 992–1001. IOS Press
  31. Il2m: Class incremental learning with dual memory. In Proceedings of the IEEE/CVF International Conference on Computer Vision, pages 583–592
  32. Scail: Classifier weights scaling for class incremental learning. In Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision, pages 1266–1275
  33. Generalisation Guarantees for Continual Learning with Orthogonal Gradient Descent
  34. Frederik Benzing. Unifying importance based regularisation methods for continual learning. In International Conference on Artificial Intelligence and Statistics, pages 2372–2396. PMLR
  35. Comps: Continual meta policy search. In International Conference on Learning Representations
  36. Task-aware information routing from common representation space in lifelong learning. In International Conference on Learning Representations
  37. Doodle it yourself: Class incremental learning by drawing a few sketches. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 2293–2302
  38. Continual lifelong learning in natural language processing: A survey. In Proceedings of the 28th International Conference on Computational Linguistics, pages 6523–6541
  39. On the Opportunities and Risks of Foundation Models
  40. On the Effectiveness of Lipschitz-Driven Rehearsal in Continual Learning
  41. Coresets via bilevel optimization for continual learning and streaming. Advances in Neural Information Processing Systems, 33:14879–14890
  42. Class-incremental continual learning into the extended der-verse. IEEE Transactions on Pattern Analysis and Machine Intelligence
  43. Transfer without Forgetting
  44. Continual semi-supervised learning through contrastive interpolation consistency. Pattern Recognition Letters, 162:9–14
  45. Machine unlearning. In 2021 IEEE Symposium on Security and Privacy (SP), pages 141–159. IEEE
  46. Language models are few-shot learners. Advances in Neural Information Processing Systems, 33:1877–1901
  47. Dark experience for general continual learning: a strong, simple baseline. Advances in Neural Information Processing Systems, 33:15920–15930
  48. New insights on reducing abrupt representation change in online continual learning. In International Conference on Learning Representations
  49. Online learned continual compression with adaptive quantization modules. In International Conference on Machine Learning, pages 1240–1250. PMLR
  50. Online fast adaptation and knowledge accumulation (osaka): a new approach to continual learning. Advances in Neural Information Processing Systems, 33:16532–16545
  51. Online continual learning with natural distribution shifts: An empirical study with visual data. In Proceedings of the IEEE/CVF International Conference on Computer Vision, pages 8281–8290
  52. Continual learning for neural machine translation. In Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, pages 3964–3974
  53. Hippocampal replay in the awake state: a potential substrate for memory consolidation and retrieval. Nature neuroscience, 14(2):147–153
  54. End-to-end incremental learning. In Proceedings of the European Conference on Computer Vision, pages 233–248
  55. Re-evaluating circuit mechanisms underlying pattern separation. Neuron, 101(4):584–602
  56. Incremental learning in semantic segmentation from image labels. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 4371–4381
  57. Modeling the background for incremental learning in semantic segmentation. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 9233–9242
  58. Co2l: Contrastive continual learning. In Proceedings of the IEEE/CVF International Conference on Computer Vision, pages 9516–9525
  59. Swad: Domain generalization by seeking flat minima. Advances in Neural Information Processing Systems, 34:22405–22418
  60. Rebalancing Batch Normalization for Exemplar-based Class-Incremental Learning
  61. Cpr: Classifier-projection regularization for continual learning. In International Conference on Learning Representations
  62. Ssul: Semantic segmentation with unknown label for exemplar-based class-incremental learning. Advances in Neural Information Processing Systems, 34:10919–10930
  63. Active bias: Training more accurate neural networks by emphasizing high variance samples. Advances in Neural Information Processing Systems, 30
  64. Riemannian walk for incremental learning: Understanding forgetting and intransigence. In Proceedings of the European Conference on Computer Vision, pages 532–547
  65. Using hindsight to anchor past knowledge in continual learning. In Proceedings of the AAAI Conference on Artificial Intelligence, volume 35, pages 6993–7001
  66. Continual learning in low-rank orthogonal subspaces. Advances in Neural Information Processing Systems, 33:9900–9911
  67. Efficient lifelong learning with a-gem. In International Conference on Learning Representations
  68. On Tiny Episodic Memories in Continual Learning
  69. Class gradient projection for continual learning. In Proceedings of the ACM International Conference on Multimedia, pages 5575–5583
  70. Mitigating forgetting in online continual learning via instance-aware parameterization. Advances in Neural Information Processing Systems, 33:17466–17477
  71. Few-shot incremental learning for label-to-image translation. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 3697–3707
  72. Lifelong machine learning. Synthesis Lectures on Artificial Intelligence and Machine Learning, 12(3):1–207
  73. Semantic-aware knowledge distillation for few-shot class-incremental learning. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 2534–2543
  74. Synthesized feature based few-shot class-incremental learning on a mixture of subspaces. In Proceedings of the IEEE/CVF International Conference on Computer Vision, pages 8661–8670
  75. Metafscil: A meta-learning approach for few-shot class incremental learning. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 14166–14175
  76. Ron Chrisley. Embodied artificial intelligence. Artificial intelligence, 149(1):131–150
  77. Online continual learning from imbalanced data. In International Conference on Machine Learning, pages 1952–1961. PMLR
  78. Continual learning for affective robotics: Why, what and how? In IEEE International Conference on Robot and Human Interactive Communication, pages 425–431. IEEE
  79. Ongoing in vivo experience triggers synaptic metaplasticity in the neocortex. Science, 319(5859):101–104
  80. Coordinated and compartmentalized neuromodulation shapes sensory processing in drosophila. Cell, 163(7):1742–1755
  81. Routing Networks with Co-training for Continual Learning
  82. Gan memory with no forgetting. Advances in Neural Information Processing Systems, 33:16481–16494
  83. Continual Pre-Training Mitigates Forgetting in Language and Vision
  84. On out-of-distribution detection with Bayesian neural networks
  85. Probing representation forgetting in supervised and unsupervised continual learning. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 16712–16721
  86. Hippocampal replay of extended experience. Neuron, 63(4):497–507
  87. A continual learning survey: Defying forgetting in classification tasks. IEEE Transactions on Pattern Analysis and Machine Intelligence, 44(7):3366–3385
  88. Continual prototype evolution: Learning online from non-stationary data streams. In Proceedings of the IEEE/CVF International Conference on Computer Vision, pages 8250–8259
  89. Episodic memory in lifelong language learning. Advances in Neural Information Processing Systems, 32
  90. Ratt: Recurrent attention to transient tasks for continual image captioning. Advances in Neural Information Processing Systems, 33:16736–16748
  91. Flattening sharpness for dynamic gradient projection memory benefits continual learning. Advances in Neural Information Processing Systems, 34:18710–18721
  92. Kernel continual learning. In International Conference on Machine Learning, pages 2621–2631. PMLR
  93. BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding
  94. Learning without memorizing. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 5138–5146
  95. Diffusion models beat gans on image synthesis. Advances in Neural Information Processing Systems, 34:8780–8794
  96. A theoretical analysis of catastrophic forgetting through the ntk overlap matrix. In International Conference on Artificial Intelligence and Statistics, pages 1072–1080. PMLR
  97. Continual Learning Beyond a Single Model
  98. Federated class-incremental learning. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 10164–10173
  99. Bridging non co-occurrence with unlabeled in-the-wild data for incremental object detection. Advances in Neural Information Processing Systems, 34:30492–30503
  100. Few-shot class-incremental learning via relation knowledge distillation. In Proceedings of the AAAI Conference on Artificial Intelligence, volume 35, pages 1255–1263
  101. Inability to activate rac1-dependent forgetting contributes to behavioral inflexibility in mutants of multiple autism-risk genes. Proceedings of the National Academy of Sciences, 113(27):7644–7649
  102. Plop: Learning without forgetting for continual semantic segmentation. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 4040–4050
  103. Podnet: Pooled outputs distillation for small-tasks incremental learning. In European Conference on Computer Vision, pages 86–102. Springer
  104. Dytox: Transformers for continual learning with dynamic token expansion. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 9285–9295
  105. Kenji Doya. What are the computations of the cerebellum, the basal ganglia and the cerebral cortex? Neural Networks, 12(7-8):961–974
  106. Kenji Doya. Complementary roles of basal ganglia and cerebellum in learning and motor control. Current opinion in neurobiology, 10(6):732–739
  107. Efficient perturbation inference and expandable network for continual learning. Neural Networks
  108. A survey of embodied ai: From simulators to research tasks. IEEE Transactions on Emerging Topics in Computational Intelligence
  109. Uncertainty-guided continual learning with bayesian neural networks. In International Conference on Learning Representations
  110. Adversarial continual learning. In European Conference on Computer Vision, pages 386–402. Springer
  111. Remembering for the right reasons: Explanations reduce catastrophic forgetting. In International Conference on Learning Representations
  112. The Turking Test: Can Language Models Understand Instructions?
  113. Boovae: Boosting approach for continual learning of vae. Advances in Neural Information Processing Systems, 34:17889–17901
  114. Memory efficient continual learning with transformers. 2022.
  115. Parvalbumin+ interneurons obey unique connectivity rules and establish a powerful lateral-inhibition microcircuit in dentate gyrus. Nature Communications, 9(1):1–10
  116. Orthogonal gradient descent for continual learning. In International Conference on Artificial Intelligence and Statistics, pages 3762–3773. PMLR
  117. Overcoming catastrophic forgetting in incremental object detection via elastic response distillation. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 9427–9436
  118. PathNet: Evolution Channels Gradient Descent in Super Neural Networks
  119. Self-supervised models are continual learners. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 9621–9630
  120. Online continual learning under extreme memory constraints. In European Conference on Computer Vision, pages 720–735. Springer
  121. Model-agnostic meta-learning for fast adaptation of deep networks. In International Conference on Machine Learning, pages 1126–1135. PMLR
  122. Orthogonal representations for robust context-dependent task performance in brains and neural networks. Neuron, 110(7):1258–1270
  123. Sharpness-aware minimization for efficiently improving generalization. In International Conference on Learning Representations
  124. Continual semantic segmentation leveraging image-level labels and rehearsal
  125. The organization of recent and remote memories. Nature Reviews Neuroscience, 6(2):119–130
  126. Stan Franklin. Autonomous agents as embodied ai. Cybernetics & Systems, 28(6):499–520
  127. Continuous scene representations for embodied ai. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 14849–14859
  128. Self-Supervised Training Enhances Online Continual Learning
  129. Incremental few-shot instance segmentation. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 1185–1194
  130. R-DFCIL: Relation-Guided Representation Learning for Data-Free Class Incremental Learning
  131. Towards continual learning for multilingual machine translation via vocabulary substitution. In Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, pages 1184–1192
  132. Loss surfaces, mode connectivity, and fast ensembling of dnns. Advances in Neural Information Processing Systems, 31
  133. Dynamic dialogue policy for continual reinforcement learning. In Proceedings of the 29th International Conference on Computational Linguistics, pages 266–284
  134. Continual learning for task-oriented dialogue system with iterative network pruning, expanding and masking. In Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 2: Short Papers), pages 517–523
  135. Dynamic VAEs with Generative Replay for Continual Zero-shot Learning
  136. Ross Girshick. Fast r-cnn. In Proceedings of the IEEE International Conference on Computer Vision, pages 1440–1448
  137. Mixed-privacy forgetting in deep networks. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 792–801
  138. Eternal sunshine of the spotless net: Selective forgetting in deep networks. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 9304–9312
  139. Continual Learning via Neural Pruning
  140. Continual pre-training of language models for math problem understanding with syntax-aware memory network. In Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 5923–5933
  141. Knowledge capture and replay for continual learning. In Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision, pages 10–18
  142. Knowledge distillation: A survey. International Journal of Computer Vision, 129(6):1789–1819
  143. Psycholinguistics meets continual learning: Measuring catastrophic forgetting in visual question answering. In Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics, pages 3601–3605
  144. Investigating catastrophic forgetting during continual training for neural machine translation. In Proceedings of the 28th International Conference on Computational Linguistics, pages 4315–4326
  145. Class-incremental instance segmentation via multi-teacher networks. In Proceedings of the AAAI Conference on Artificial Intelligence, volume 35, pages 1478–1486
  146. Not just selection, but exploration: Online class-incremental continual learning via dual view consistency. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 7442–7451
  147. Adaptive orthogonal projection for batch and online continual learning. 2
  148. Online continual learning through mutual information maximization. In International Conference on Machine Learning, pages 8109–8126. PMLR
  149. Look-ahead meta learning for continual learning. Advances in Neural Information Processing Systems, 33:11588–11598
  150. Nispa: Neuro-inspired stability-plasticity adaptation for continual learning in sparse networks. In International Conference on Machine Learning, pages 8157–8174. PMLR
  151. Embracing change: Continual learning in deep neural networks. Trends in Cognitive Sciences, 24(12):1028–1040
  152. Econet: Effective continual pretraining of language models for event temporal reasoning. In Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing, pages 5367–5380
  153. Pre-trained models: Past, present and future. AI Open, 2:225–250
  154. Visualizing and understanding the effectiveness of bert. In Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP), pages 4143–4152
  155. An end-to-end architecture for class-incremental object detection with knowledge distillation. In IEEE International Conference on Multimedia and Expo, pages 1–6. IEEE
  156. The elements of statistical learning: data mining, inference, and prediction, volume 2. Springer
  157. Labelling and optical erasure of synaptic memory traces in the motor cortex. Nature, 525(7569):333–338
  158. Remind your neural network to prevent catastrophic forgetting. In European Conference on Computer Vision, pages 466–483. Springer
  159. Replay in deep learning: Current approaches and missing biological elements. Neural Computation, 33(11):2908–2950
  160. Exemplar-supported generative reproduction for class incremental learning. In BMVC, page 98
  161. Incremental learning in online scenario. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 13926–13935
  162. Online continual learning via candidates voting. In Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision, pages 3154–3163
  163. Posterior meta-replay for continual learning. Advances in Neural Information Processing Systems, 34:14135–14149
  164. Constrained few-shot class-incremental learning. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 9057–9067
  165. Flat minima. Neural Computation, 9(1):1–42
  166. Lifelong learning via progressive distillation and retrospection. In Proceedings of the European Conference on Computer Vision, pages 437–452
  167. Learning a unified classifier incrementally via rebalancing. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 831–839
  168. Parameter-efficient transfer learning for nlp. In International Conference on Machine Learning, pages 2790–2799. PMLR
  169. Re-evaluating Continual Learning Scenarios: A Categorization and Case for Strong Baselines
  170. How well does self-supervised pre-training perform with streaming data? In International Conference on Learning Representations
  171. One Pass ImageNet
  172. Overcoming catastrophic forgetting for continual learning via model adaptation. In International Conference on Learning Representations
  173. Continual learning by using information of each class holistically. In Proceedings of the AAAI Conference on Artificial Intelligence, volume 35, pages 7797–7805
  174. Distilling causal effect of data in class-incremental learning. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 3957–3966
  175. Continual learning for text classification with information disentanglement based regularization. In Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, pages 2736–2746
  176. AlterSGD: Finding Flat Minima for Continual Learning by Alternative Training
  177. Compacting, picking and growing for unforgetting continual learning. Advances in Neural Information Processing Systems, 32
  178. Optimizing reusable knowledge for continual learning via metalearning. Advances in Neural Information Processing Systems, 34:14150–14162
  179. On Quadratic Penalties in Elastic Weight Consolidation
  180. Incremental task learning with incremental rank updates. In European Conference on Computer Vision, pages 566–582. Springer
  181. Origins of cell-type-specific olfactory processing in the drosophila mushroom body circuit. Neuron, 95(2):357–367
  182. Batch normalization: Accelerating deep network training by reducing internal covariate shift. In International Conference on Machine Learning, pages 448–456. PMLR
  183. Memory-efficient incremental learning through feature adaptation. In European Conference on Computer Vision, pages 699–715. Springer
  184. Selective experience replay for lifelong learning. In Proceedings of the AAAI Conference on Artificial Intelligence, volume 32
  185. Averaging Weights Leads to Wider Optima and Better Generalization
  186. Adaptive mixtures of local experts. Neural Computation, 3(1):79–87
  187. Towards continual knowledge learning of language models. In International Conference on Learning Representations
  188. A simple baseline that questions the use of pretrained-models in continual learning. In NeurIPS 2022 Workshop on Distribution Shifts: Connecting Methods and Applications.
  189. Meta-learning representations for continual learning. Advances in Neural Information Processing Systems, 32
  190. Contributions by metaplasticity to solving the catastrophic forgetting problem. Trends in Neurosciences
  191. Reconciling meta-learning and continual learning with online mixtures of tasks. Advances in Neural Information Processing Systems, 32
  192. FedSpeech: Federated Text-to-Speech with Continual Learning
  193. Helpful or harmful: Inter-task association in continual learning. In European Conference on Computer Vision, pages 519–535. Springer
  194. Learn continually, generalize rapidly: Lifelong knowledge accumulation for few-shot learning. In Findings of the Association for Computational Linguistics: EMNLP 2021, pages 714–729
  195. Gradient-based editing of memory examples for online task-free continual learning. Advances in Neural Information Processing Systems, 34:29193–29205
  196. Energy-based latent aligner for incremental learning. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 7452–7461
  197. Towards open world object detection. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 5830–5840
  198. Novel class discovery without forgetting. In European Conference on Computer Vision, pages 570–586. Springer
  199. Continual learning with node-importance based adaptive group sparse regularization. Advances in Neural Information Processing Systems, 33:3647–3658
  200. S3c: Self-supervised stochastic classifiers for few-shot class-incremental learning. In European Conference on Computer Vision, pages 432–448. Springer
  201. Reparameterizing convolutions for incremental multi-task learning without task interference. In European Conference on Computer Vision, pages 689–707. Springer
  202. Forget-free continual learning with winning subnetworks. In International Conference on Machine Learning, pages 10734–10750. PMLR
  203. Class-incremental learning by knowledge distillation with adaptive feature consolidation. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 16071–16080
  204. A soft nearest-neighbor framework for continual semi-supervised learning
  205. Natural continual learning: success is a journey, not (just) a destination. Advances in Neural Information Processing Systems, 34:28067–28079
  206. Continual Reinforcement Learning with Multi-Timescale Replay
  207. Continual reinforcement learning with complex synapses. In International Conference on Machine Learning, pages 2497–2506. PMLR
  208. Policy consolidation for continual reinforcement learning. In International Conference on Machine Learning, pages 3242–3251. PMLR
  209. Variational auto-regressive gaussian processes for continual learning. In International Conference on Machine Learning, pages 5290–5300. PMLR
  210. Learning curves for continual learning in neural networks: Self-knowledge transfer and forgetting. In International Conference on Learning Representations
  211. Continual Training of Language Models for Few-Shot Learning
  212. Continual Learning of Natural Language Processing Tasks: A Survey
  213. Continual learning of a mixed sequence of similar and dissimilar tasks. Advances in Neural Information Processing Systems, 33:18493–18504
  214. Achieving forgetting prevention and knowledge transfer in continual learning. Advances in Neural Information Processing Systems, 34:22443–22456
  215. Adapting bert for continual learning of a sequence of aspect sentiment classification tasks. In Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, pages 4746–4755
  216. Fearnet: Brain-inspired model for incremental learning. In International Conference on Learning Representations
  217. On large-batch training for deep learning: Generalization gap and sharp minima. In International Conference on Learning Representations
  218. Same state, different task: Continual reinforcement learning without interference. In Proceedings of the AAAI Conference on Artificial Intelligence, volume 36, pages 7143–7151
  219. Towards continual reinforcement learning: A review and perspectives. Journal of Artificial Intelligence Research, 75:1401–1476
  220. Towards Label-Efficient Incremental Learning: A Survey
  221. Imbalanced continual learning with partitioning reservoir sampling. In European Conference on Computer Vision, pages 411–428. Springer
  222. Continual learning on noisy data streams via self-purified replay. In Proceedings of the IEEE/CVF international conference on computer vision, pages 537–547
  223. A Theoretical Study on Solving Continual Learning
  224. Split-and-bridge: Adaptable class incremental learning within a single neural network. In Proceedings of the AAAI Conference on Artificial Intelligence, volume 35, pages 8137–8145
  225. Dygrain: An incremental learning framework for dynamic graphs
  226. Segment Anything
  227. Overcoming catastrophic forgetting in neural networks. Proceedings of the National Academy of Sciences, 114(13):3521–3526
  228. Meta-consolidation for continual learning. Advances in Neural Information Processing Systems, 33:14374–14386
  229. Incremental object detection via meta-learning. IEEE Transactions on Pattern Analysis and Machine Intelligence
  230. Optimal continual learning has perfect memory and is np-hard. In International Conference on Machine Learning, pages 5327–5337. PMLR
  231. Online continual learning on class incremental blurry task configuration with anytime inference. In International Conference on Learning Representations
  232. Balancing stability and plasticity through advanced null space in continual learning. In European Conference on Computer Vision, pages 219–236. Springer
  233. Imagenet classification with deep convolutional neural networks. In Proceedings of the Advances in Neural Information Processing Systems, volume 25, pages 1097–1105
  234. Biological underpinnings for lifelong learning machines. Nature Machine Intelligence, 4(3):196–210
  235. Generalized and incremental few-shot learning by explicit learning and calibration without forgetting. In Proceedings of the IEEE/CVF International Conference on Computer Vision, pages 9020–9029
  236. Determinantal point processes for machine learning. Foundations and Trends® in Machine Learning, 5(2–3):123–286
  237. Bayesian structural adaptation for continual learning. In International Conference on Machine Learning, pages 5850–5860. PMLR
  238. What learning systems do intelligent agents need? complementary learning systems theory updated. Trends in cognitive sciences, 20(7):512–534
  239. Retrospective adversarial replay for continual learning
  240. Continual learning with bayesian neural networks for non-stationary data. In International Conference on Learning Representations
  241. Do not forget to attend to uncertainty while mitigating catastrophic forgetting. In Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision, pages 736–745
  242. Semi-supervised class incremental learning. In International Conference on Pattern Recognition, pages 10383–10389. IEEE
  243. Few-shot and continual learning with attentive independent mechanisms. In Proceedings of the IEEE/CVF International Conference on Computer Vision, pages 9455–9464
  244. Continual learning with extended kronecker-factored approximate curvature. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 9001–9010
  245. Residual continual learning. In Proceedings of the AAAI Conference on Artificial Intelligence, volume 34, pages 4553–4560
  246. Overcoming catastrophic forgetting with unlabeled data in the wild. In Proceedings of the IEEE/CVF International Conference on Computer Vision, pages 312–321
  247. Infomax-gan: Improved adversarial image generation via information maximization and contrastive learning. In Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision, pages 3942–3952
  248. Continual learning in the teacher-student setup: Impact of task similarity. In International Conference on Machine Learning, pages 6109–6119. PMLR
  249. A neural dirichlet process mixture model for task-free continual learning. In International Conference on Learning Representations
  250. Overcoming catastrophic forgetting by incremental moment matching. Advances in Neural Information Processing Systems, 30
  251. Continual learning for robotics: Definition, framework, learning strategies, opportunities and challenges. Information Fusion, 58:52–68
  252. The power of scale for parameter-efficient prompt tuning. In Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing, pages 3045–3059
  253. Detecting and Adapting to Irregular Distribution Shifts in Bayesian Online Learning
  254. Overcoming catastrophic forgetting during domain adaptation of seq2seq language generation. In Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, pages 5441–5454
  255. Rilod: Near real-time incremental learning for object detection at the edge. In Proceedings of the 4th ACM/IEEE Symposium on Edge Computing, pages 113–126
  256. Continual few-shot intent detection. In Proceedings of the 29th International Conference on Computational Linguistics, pages 333–343
  257. Federated optimization in heterogeneous networks. Proceedings of Machine Learning and Systems, 2:429–450
  258. Generalized focal loss: Learning qualified and distributed bounding boxes for dense object detection. Advances in Neural Information Processing Systems, 33:21002–21012
  259. Learn to grow: A continual structure learning framework for overcoming catastrophic forgetting. In International Conference on Machine Learning, pages 3925–3934. PMLR
  260. Learning without forgetting. IEEE Transactions on Pattern Analysis and Machine Intelligence, 40(12):2935–2947
  261. Total recall: a customized continual learning method for neural semantic parsers. In Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing, pages 3816–3831
  262. Balancing between forgetting and acquisition in incremental subpopulation learning. In European Conference on Computer Vision, pages 364–380. Springer
  263. Towards better plasticity-stability trade-off in incremental learning: A simple linear connector. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 89–98
  264. Prototype-guided continual adaptation for class-incremental unsupervised domain adaptation. In European Conference on Computer Vision, pages 351–368. Springer
  265. Trgp: Trust region gradient projection for continual learning. In International Conference on Learning Representations
  266. Beyond Not-Forgetting: Continual Learning with Backward Knowledge Transfer
  267. Focal loss for dense object detection. In Proceedings of the IEEE International Conference on Computer Vision, pages 2980–2988
  268. Lifelong and continual learning dialogue systems: learning during conversation. In Proceedings of the AAAI Conference on Artificial Intelligence, volume 35, pages 15058–15063
  269. Few-shot class-incremental learning via entropy-regularized data-free replay. In European Conference on Computer Vision, pages 146–162. Springer
  270. Continual learning with recursive gradient optimization. In International Conference on Learning Representations
  271. Incremental Prompting: Episodic Memory Prompt for Lifelong Event Detection
  272. Incremental Meta-Learning via Indirect Discriminant Alignment
  273. Lifelong Intent Detection via Multi-Strategy Rebalancing
  274. Continual learning for sentence representations using conceptors. In Proceedings of NAACL-HLT, pages 3274–3279
  275. Long-tailed class incremental learning. In European Conference on Computer Vision, pages 495–512. Springer
  276. Rotate your networks: Better weight consolidation and less catastrophic forgetting. In International Conference on Pattern Recognition, pages 2262–2268. IEEE
  277. Generative feature replay for class-incremental learning. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, pages 226–227
  278. Adaptive aggregation networks for class-incremental learning. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 2544–2553
  279. Rmm: Reinforced memory management for class-incremental learning. Advances in Neural Information Processing Systems, 34:3478–3490
  280. Mnemonics training: Multi-class incremental learning without forgetting. In Proceedings of the IEEE/CVF conference on Computer Vision and Pattern Recognition, pages 12245–12254
  281. Swin transformer: Hierarchical vision transformer using shifted windows. In Proceedings of the IEEE/CVF International Conference on Computer Vision, pages 10012–10022
  282. Continual reinforcement learning in 3d non-stationary environments. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, pages 248–249
  283. Core50: a new dataset and benchmark for continuous object recognition. In Conference on Robot Learning, pages 17–26. PMLR
  284. Generalized variational continual learning. In International Conference on Learning Representations
  285. Gradient episodic memory for continual learning. Advances in Neural Information Processing Systems, 30
  286. Dpm-solver: A fast ode solver for diffusion probabilistic model sampling in around 10 steps. In Advances in Neural Information Processing Systems
  287. Adaptive Online Planning for Continual Lifelong Learning
  288. Continual federated learning based on knowledge distillation
  289. Representational continuity for unsupervised continual learning. In International Conference on Learning Representations
  290. Continual learning in task-oriented dialogue systems. In Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing, pages 7452–7467
  291. Online continual learning in image classification: An empirical survey. Neurocomputing, 469:28–51
  292. Supervised contrastive replay: Revisiting the nearest class mean classifier in online class-incremental continual learning. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 3589–3599
  293. Piggyback: Adapting a single network to multiple tasks by learning to mask weights. In Proceedings of the European Conference on Computer Vision, pages 67–82
  294. Packnet: Adding multiple tasks to a single network by iterative pruning. In Proceedings of the IEEE conference on Computer Vision and Pattern Recognition, pages 7765–7773
  295. Recall: Replay-based continual learning in semantic segmentation. In Proceedings of the IEEE/CVF International Conference on Computer Vision, pages 7026–7035
  296. Optimizing neural networks with kronecker-factored approximate curvature. In International Conference on Machine Learning, pages 2408–2417. PMLR
  297. On Class Orderings for Incremental Learning
  298. Few-shot lifelong learning. In Proceedings of the AAAI Conference on Artificial Intelligence, volume 35, pages 2337–2345
  299. Why there are complementary learning systems in the hippocampus and neocortex: insights from the successes and failures of connectionist models of learning and memory. Psychological review, 102(3):419
  300. Catastrophic interference in connectionist networks: The sequential learning problem. In Psychology of learning and motivation, volume 24, pages 109–165. Elsevier
  301. Communication-efficient learning of deep networks from decentralized data. In Artificial Intelligence and Statistics, pages 1273–1282. PMLR
  302. Continual learning using a bayesian nonparametric dictionary of weight factors. In International Conference on Artificial Intelligence and Statistics, pages 100–108. PMLR
  303. An Empirical Investigation of the Role of Pre-training in Lifelong Learning
  304. Lifelong policy gradient learning of factored policies for faster training without forgetting. Advances in Neural Information Processing Systems, 33:14398–14409
  305. Continual learning for natural language generation in task-oriented dialog systems. In Findings of the Association for Computational Linguistics: EMNLP 2020, pages 3461–3474
  306. Generalized class incremental learning. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, pages 240–241
  307. Continual learning with filter atom swapping. In International Conference on Learning Representations
  308. Incremental learning techniques for semantic segmentation. In Proceedings of the IEEE/CVF International Conference on Computer Vision Workshops, pages 0–0
  309. Continual semantic segmentation via repulsion-attraction of sparse and disentangled latent representations. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 1114–1124
  310. Knowledge distillation for incremental learning in semantic segmentation. Computer Vision and Image Understanding, 205:103167
  311. One-Pass Learning via Bridging Orthogonal Gradient Descent and Recursive Least-Squares
  312. Wide neural networks forget less catastrophically. In International Conference on Machine Learning, pages 15699–15717. PMLR
  313. Architecture Matters in Continual Learning
  314. Dropout as an implicit gating mechanism for continual learning. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, pages 232–233
  315. Linear mode connectivity in multitask and continual learning. In International Conference on Learning Representations
  316. Understanding the role of training regimes in continual learning. Advances in Neural Information Processing Systems, 33:7308–7320
  317. The drosophila mushroom body: From architecture to algorithm in a learning circuit. Annual Review of Neuroscience, 43:465–484
  318. Continual learning for named entity recognition. In Proceedings of the AAAI Conference on Artificial Intelligence, volume 35, pages 13570–13577
  319. Continuous coordination as a realistic scenario for lifelong learning. In International Conference on Machine Learning, pages 8016–8024. PMLR
  320. What is being transferred in transfer learning? Advances in Neural Information Processing Systems, 33:512–523
  321. Variational continual learning. In International Conference on Learning Representations
  322. ALIFE: Adaptive Logit Regularizer and Feature Replay for Incremental Semantic Segmentation
  323. OpenAI. Gpt-4 technical report. 2023.
  324. Continual Learning with Foundation Models: An Empirical Study of Latent Replay
  325. Learning to remember: A synaptic plasticity driven framework for continual learning. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 11321–11329
  326. Continual learning via local module composition. Advances in Neural Information Processing Systems, 34:30298–30312
  327. Dopamine and cognitive control in prefrontal cortex. Trends in Cognitive Sciences, 23(3):213–234
  328. Overcoming catastrophic forgetting by neuron-level plasticity control. In Proceedings of the AAAI Conference on Artificial Intelligence, volume 34, pages 5339–5346
  329. Continual deep learning by functional regularisation of memorable past. Advances in Neural Information Processing Systems, 33:4453–4464
  330. First Session Adaptation: A Strong Replay-Free Baseline for Class-Incremental Learning
  331. Continual lifelong learning with neural networks: A review. Neural Networks, 113:54–71
  332. Continual learning by asymmetric loss approximation with single-side overestimation. In Proceedings of the IEEE/CVF International Conference on Computer Vision, pages 3335–3344
  333. Class-incremental learning for action recognition in videos. In Proceedings of the IEEE/CVF International Conference on Computer Vision, pages 13698–13707
  334. Continual few-shot learning for text classification. In Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing, pages 5688–5702
  335. Simpler is Better: off-the-shelf Continual Learning Through Pretrained Backbones
  336. Continual learning: a feature extraction formalization, an efficient algorithm, and fundamental obstructions
  337. Faster ilod: Incremental learning for object detectors based on faster rcnn. Pattern Recognition Letters, 140:109–115
  338. Sid: Incremental learning for anchor-free object detection via selective and inter-related distillation. Computer Vision and Image Understanding, 210:103229
  339. Few-shot class-incremental learning from an open-set perspective. In European Conference on Computer Vision, pages 382–397. Springer
  340. A pac-bayesian bound for lifelong learning. In International Conference on Machine Learning, pages 991–999. PMLR
  341. Film: Visual reasoning with a general conditioning layer. In Proceedings of the AAAI Conference on Artificial Intelligence, volume 32
  342. Incremental few-shot object detection. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 13846–13855
  343. FeTrIL: Feature Translation for Exemplar-Free Class-Incremental Learning
  344. Continual Learning with Fully Probabilistic Models
  345. Dualnet: Continual learning, fast and slow. Advances in Neural Information Processing Systems, 34:16131–16144
  346. Contextual transformation networks for online continual learning. In International Conference on Learning Representations
  347. Continual normalization: Rethinking batch normalization for online continual learning. In International Conference on Learning Representations
  348. Online task-free continual learning with dynamic sparse distributed memory. In European Conference on Computer Vision, pages 739–756. Springer
  349. Looking back on learned experiences for class/task incremental learning. In International Conference on Learning Representations
  350. Gdumb: A simple approach that questions our progress in continual learning. In European conference on computer vision, pages 524–540. Springer
  351. The Challenges of Continuous Self-Supervised Learning
  352. Lfpt5: A unified framework for lifelong few-shot language learning based on prompt tuning of t5. In International Conference on Learning Representations
  353. Continual few-shot relation learning via embedding space regularization and data augmentation. In Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 2776–2789
  354. Bns: Building network structures dynamically for continual learning. Advances in Neural Information Processing Systems, 34:20608–20620
  355. ELLE: Efficient Lifelong Pre-training for Emerging Data
  356. Recent Advances of Continual Learning in Computer Vision: An Overview
  357. Learning transferable visual models from natural language supervision. In International Conference on Machine Learning, pages 8748–8763. PMLR
  358. Random path selection for incremental learning. Advances in Neural Information Processing Systems, 3
  359. itaml: An incremental task-agnostic meta-learning approach. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 13588–13597
  360. Relationship matters: Relation guided knowledge transfer for incremental learning of object detectors. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, pages 250–251
  361. Anatomy of Catastrophic Forgetting: Hidden Representations and Task Semantics
  362. Effect of scale on catastrophic forgetting in neural networks. In International Conference on Learning Representations
  363. Model zoo: A growing brain that learns continually. In International Conference on Learning Representations
  364. Encoder based lifelong learning. In Proceedings of the IEEE International Conference on Computer Vision, pages 1320–1328
  365. Continual unsupervised representation learning. Advances in Neural Information Processing Systems, 32
  366. Progressive prompts: Continual learning for language models. In International Conference on Learning Representations
  367. icarl: Incremental classifier and representation learning. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pages 2001–2010
  368. A two-phase prototypical network model for incremental few-shot relation classification. In Proceedings of the International Conference on Computational Linguistics, pages 1618–1629
  369. Faster r-cnn: Towards real-time object detection with region proposal networks. Advances in Neural Information Processing Systems, 28
  370. The persistence and transience of memory. Neuron, 94(6):1071–1084
  371. Learning to learn without forgetting by maximizing transfer and minimizing interference. In International Conference on Learning Representations
  372. Scalable recollections for continual lifelong learning. In Proceedings of the AAAI Conference on Artificial Intelligence, volume 33, pages 1352–1359
  373. Online structured laplace approximations for overcoming catastrophic forgetting. Advances in Neural Information Processing Systems, 31
  374. Stream-51: Streaming classification and novelty detection from videos. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, pages 228–229
  375. Experience replay for continual learning. Advances in Neural Information Processing Systems, 32
  376. Generative continual concept learning. In Proceedings of the AAAI Conference on Artificial Intelligence, volume 34, pages 5545–5552
  377. Complementary learning for overcoming catastrophic forgetting using experience replay. In Proceedings of the 28th International Joint Conference on Artificial Intelligence, pages 3339–3345
  378. Detection and continual learning of novel face presentation attacks. In Proceedings of the IEEE/CVF International Conference on Computer Vision, pages 14851–14860
  379. Class-incremental novel class discovery. In European Conference on Computer Vision, pages 317–333. Springer
  380. Continual learning via sequential function-space variational inference. In International Conference on Machine Learning, pages 18871–18887. PMLR
  381. Progressive Neural Networks
  382. Gradient projection memory for continual learning. In International Conference on Learning Representations
  383. Towards a natural benchmark for continual learning. In Advances in Neural Information Processing Systems Workshops
  384. Progress & compress: A scalable framework for continual learning. In International Conference on Machine Learning, pages 4528–4537. PMLR
  385. Continual Learning in Generative Adversarial Nets
  386. Overcoming catastrophic forgetting with hard attention to the task. In International Conference on Machine Learning, pages 4548–4557. PMLR
  387. Overcoming catastrophic forgetting beyond continual learning: Balanced training for neural machine translation. In Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 2023–2036
  388. A progressive model to enable continual learning for semantic slot filling. In Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP), pages 1279–1284
  389. Overcoming catastrophic forgetting in incremental few-shot learning by finding flat minima. Advances in Neural Information Processing Systems, 34:6747–6761
  390. Incremental few-shot semantic segmentation via embedding adaptive-update and hyper-class representation. In Proceedings of the ACM International Conference on Multimedia, pages 5547–5556
  391. Mimicking the oracle: An initial phase decorrelation approach for class incremental learning. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 16722–16731
  392. Learning with selective forgetting. In IJCAI, volume 2, page 6
  393. Online class-incremental continual learning with adversarial shapley value. In Proceedings of the AAAI Conference on Artificial Intelligence, volume 35, pages 9630–9638
  394. Continual learning with deep generative replay. Advances in Neural Information Processing Systems, 30
  395. Incremental learning of object detectors without catastrophic forgetting. In Proceedings of the IEEE International Conference on Computer Vision, pages 3400–3409
  396. Dlcft: Deep linear continual fine-tuning for general incremental learning. In European Conference on Computer Vision, pages 513–529. Springer
  397. On generalizing beyond domains in cross-domain continual learning. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 9265–9274
  398. On learning the geodesic path for incremental learning. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 1591–1600
  399. Rectification-based knowledge retention for continual learning. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 15282–15291
  400. Calibrating cnns for lifelong learning. Advances in Neural Information Processing Systems, 33:15579–15590
  401. Always be dreaming: A new approach for data-free class-incremental learning. In Proceedings of the IEEE/CVF International Conference on Computer Vision, pages 9374–9384
  402. Coda-prompt: Continual decomposed attention-based prompting for rehearsal-free continual learning. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 11909–11919
  403. Score-based generative modeling through stochastic differential equations. In International Conference on Learning Representations
  404. CLiMB: A Continual Learning Benchmark for Vision-and-Language Tasks
  405. Dropout: a simple way to prevent neural networks from overfitting. The Journal of Machine Learning Research, 15(1):1929–1958
  406. Unsupervised model adaptation for continual semantic segmentation. In Proceedings of the AAAI Conference on Artificial Intelligence, volume 35, pages 2593–2601
  407. Lamol: Language modeling for lifelong language learning. In International Conference on Learning Representations
  408. Distill and replay for continual language learning. In Proceedings of the 28th international conference on computational linguistics, pages 3569–3579
  409. Exploring Example Influence in Continual Learning
  410. Information-theoretic online memory selection for continual learning. In International Conference on Learning Representations
  411. Ernie 2.0: A continual pre-training framework for language understanding. In Proceedings of the AAAI Conference on Artificial Intelligence, volume 34, pages 8968–8975
  412. Improving and Understanding Variational Continual Learning
  413. Layerwise optimization by gradient decomposition for continual learning. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 9634–9643
  414. Learning to imagine: Diversify memory for incremental learning using unlabeled data. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 9549–9558
  415. Topology-preserving class-incremental learning. In European Conference on Computer Vision, pages 254–270. Springer
  416. Few-shot class-incremental learning. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 12183–12192
  417. A deep hierarchical approach to lifelong learning in minecraft. In Proceedings of the AAAI Conference on Artificial Intelligence, volume 31
  418. Catastrophic forgetting and mode collapse in gans. In International Joint Conference on Neural Networks, pages 1–10. IEEE
  419. Functional regularisation for continual learning with gaussian processes. In International Conference on Learning Representations
  420. Gcr: Gradient coreset based replay buffer selection for continual learning. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 99–108
  421. Bring evanescent representations to life in lifelong class incremental learning. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 16732–16741
  422. Natural variational continual learning
  423. A modeling framework for adaptive lifelong learning with transfer and savings through gating in the prefrontal cortex. Proceedings of the National Academy of Sciences, 117(47):29872–29882
  424. Brain-inspired replay for continual learning with artificial neural networks. Nature Communications, 11(1):1–14
  425. Three scenarios for continual learning
  426. Neural discrete representation learning. Advances in Neural Information Processing Systems, 30
  427. Prompt augmented generative replay via supervised contrastive learning for lifelong intent detection. In Findings of the Association for Computational Linguistics: NAACL 2022, pages 1113–1127
  428. Attention is all you need. Advances in Neural Information Processing Systems, 30
  429. Efficient continual learning with modular networks and task-driven priors. In International Conference on Learning Representations
  430. Rehearsal revealed: The limits and merits of revisiting samples in continual learning. In Proceedings of the IEEE/CVF International Conference on Computer Vision, pages 9385–9394
  431. vclimb: A novel video class incremental learning benchmark. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 19035–19044
  432. Jeffrey S Vitter. Random sampling with a reservoir. ACM Transactions on Mathematical Software (TOMS), 11(1):37–57
  433. Continual learning with hypernetworks. In International Conference on Learning Representations
  434. Scott Waddell. Neural plasticity: Dopamine tunes the mushroom body output network. Current Biology, 26(3):R109–R112
  435. Mell: Large-scale extensible user intent classification for dialogue systems with meta lifelong learning. In Proceedings of the 27th ACM SIGKDD Conference on Knowledge Discovery & Data Mining, pages 3649–3659
  436. Lifelong graph learning. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 13719–13728
  437. FOSTER: Feature Boosting and Compression for Class-Incremental Learning
  438. Wanderlust: Online continual object detection in the real world. In Proceedings of the IEEE/CVF International Conference on Computer Vision, pages 10829–10838
  439. Acae-remind for online continual learning with compressed feature replay. Pattern Recognition Letters, 150:122–129
  440. Triple-memory networks: A brain-inspired method for continual learning. IEEE Transactions on Neural Networks and Learning Systems, 33(5):1925–1934
  441. Ordisco: Effective and efficient usage of incremental unlabeled data for semi-supervised continual learning. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 5383–5392
  442. Afec: Active forgetting of negative transfer in continual learning. Advances in Neural Information Processing Systems, 34:22379–22391
  443. Coscl: Cooperation of small continual learners is stronger than a big one. In European Conference on Computer Vision, pages 254–271. Springer
  444. Memory replay with data compression for continual learning. In International Conference on Learning Representations
  445. Learngene: From open-world to your learning task. In Proceedings of the AAAI Conference on Artificial Intelligence, volume 36, pages 8557–8565
  446. Anti-retroactive interference for lifelong learning. In European Conference on Computer Vision, pages 163–178. Springer
  447. Few-shot class-incremental learning for named entity recognition. In Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 571–582
  448. Training networks in null space of feature covariance for continual learning. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 184–193
  449. Incremental learning from scratch for task-oriented dialogue systems. In Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics, pages 3710–3720
  450. S-Prompts Learning with Pre-trained Transformers: An Occam's Razor for Domain Incremental Learning
  451. Continual learning with lifelong vision transformer. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 171–181
  452. Continual learning through retrieval and imagination. In Proceedings of the AAAI Conference on Artificial Intelligence, volume 8
  453. Online continual learning with contrastive vision transformer. In European Conference on Computer Vision, pages 631–650. Springer
  454. Efficient meta lifelong-learning with limited memory. In Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP), pages 535–548
  455. Improving task-free continual learning by distributionally robust memory evolution. In International Conference on Machine Learning, pages 22985–22998. PMLR
  456. Meta-learning with less forgetting on large-scale non-stationary task distributions. In European Conference on Computer Vision, pages 221–238. Springer
  457. DualPrompt: Complementary Prompting for Rehearsal-free Continual Learning
  458. Learning to prompt for continual learning. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 139–149
  459. Continual learning with guarantees via weight interval constraints. In International Conference on Machine Learning, pages 23897–23911. PMLR
  460. Disentangling Transfer in Continual Reinforcement Learning
  461. Continual world: A robotic benchmark for continual reinforcement learning. Advances in Neural Information Processing Systems, 34:28496–28510
  462. Model soups: averaging weights of multiple fine-tuned models improves accuracy without increasing inference time. In International Conference on Machine Learning, pages 23965–23998. PMLR
  463. Supermasks in superposition. Advances in Neural Information Processing Systems, 33:15173–15184
  464. Memory replay gans: Learning to generate new categories without forgetting. Advances in Neural Information Processing Systems, 31
  465. Striking a balance between stability and plasticity for class-incremental learning. In Proceedings of the IEEE/CVF International Conference on Computer Vision, pages 1124–1133
  466. Pretrained language model in continual learning: A comparative study. In International Conference on Learning Representations
  467. Curriculum-meta learning for order-robust continual relation extraction. In Proceedings of the AAAI Conference on Artificial Intelligence, volume 35, pages 10363–10369
  468. Class-incremental learning with strong pre-trained models. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 9601–9610
  469. Large scale incremental learning. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 374–382
  470. Deltagrad: Rapid retraining of machine learning models. In International Conference on Machine Learning, pages 10355–10366. PMLR
  471. Incremental learning via rate reduction. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 1125–1133
  472. Incremental few-shot text classification with multi-round new classes: Formulation, dataset and system. In Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, pages 1351–1360
  473. Incremental learning using conditional adversarial networks. In Proceedings of the IEEE/CVF International Conference on Computer Vision, pages 6619–6628
  474. General incremental learning with domain-aware categorical representations. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 14351–14360
  475. Geometry of sequence working memory in macaque prefrontal cortex. Science, 375(6581):632–639
  476. Reinforced continual learning. Advances in Neural Information Processing Systems, 31
  477. Continual learning of control primitives: Skill discovery via reset-games. Advances in Neural Information Processing Systems, 33:4999–5010
  478. Meta-attention for vit-backed continual learning. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 150–159
  479. Generative negative text replay for continual vision-language pretraining. In European Conference on Computer Vision, pages 22–38. Springer
  480. Der: Dynamically expandable representation for class incremental learning. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 3014–3023
  481. An em framework for online incremental learning of semantic segmentation. In Proceedings of the ACM International Conference on Multimedia, pages 3052–3060
  482. Uncertainty-aware contrastive distillation for incremental semantic segmentation. IEEE Transactions on Pattern Analysis and Machine Intelligence
  483. Stably maintained dendritic spines are associated with lifelong memories. Nature, 462(7275):920–924
  484. Learning latent representations across multiple data domains using lifelong vaegan. In European Conference on Computer Vision, pages 777–795. Springer
  485. Task-Free Continual Learning via Online Discrepancy Distance Learning
  486. Learning with recoverable forgetting. In European Conference on Computer Vision, pages 87–103. Springer
  487. Mitigating forgetting in online continual learning with neuron calibration. Advances in Neural Information Processing Systems, 34:10260–10272
  488. Dreaming to distill: Data-free knowledge transfer via deepinversion. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 8715–8724
  489. Contintin: Continual learning from task instructions. In Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 3062–3072
  490. Federated continual learning with weighted inter-client transfer. In International Conference on Machine Learning, pages 12073–12086. PMLR
  491. Scalable and order-robust continual learning with additive parameter decomposition. In International Conference on Learning Representations
  492. Online coreset selection for rehearsal-based continual learning. In International Conference on Learning Representations
  493. Lifelong learning with dynamically expandable networks. In International Conference on Learning Representations
  494. Continual Learning by Modeling Intra-Class Variation
  495. Self-training for class-incremental semantic segmentation. IEEE Transactions on Neural Networks and Learning Systems
  496. Semantic drift compensation for class-incremental learning. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 6982–6991
  497. Continual learning of context-dependent processing in neural networks. Nature Machine Intelligence, 1(8):364–372
  498. Continual learning through synaptic intelligence. In International Conference on Machine Learning, pages 3987–3995. PMLR
  499. Piggyback gan: Efficient lifelong learning for image conditioned generation. In European Conference on Computer Vision, pages 397–413. Springer
  500. Hyper-lifelonggan: scalable lifelong learning for image conditioned generation. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 2246–2255
  501. Lifelong gan: Continual learning for conditional image generation. In Proceedings of the IEEE/CVF International Conference on Computer Vision, pages 2759–2768
  502. Few-shot incremental learning with continually evolved classifiers. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 12455–12464
  503. Representation compensation networks for continual semantic segmentation. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 7053–7064
  504. SLCA: Slow Learner with Classifier Alignment for Continual Learning on a Pre-trained Model
  505. Mixup: Beyond empirical risk minimization. In International Conference on Learning Representations
  506. Class-incremental learning via deep model consolidation. In Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision, pages 1131–1140
  507. Side-tuning: a baseline for network adaptation via additive side networks. In European Conference on Computer Vision, pages 698–714. Springer
  508. Active protection: Learning-activated raf/mapk activity protects labile memory from rac1-independent forgetting. Neuron, 98(1):142–155
  509. Cglb: Benchmark tasks for continual graph learning. In Thirty-sixth Conference on Neural Information Processing Systems Datasets and Benchmarks Track
  510. Epicker is an exemplar-based continual learning approach for knowledge accumulation in cryoem particle picking. Nature Communications, 13(1):1–10
  511. A simple but strong baseline for online continual learning: Repeated Augmented Rehearsal
  512. Continual sequence generation with adaptive compositional modules. In Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 3653–3667
  513. Maintaining discrimination and fairness in class incremental learning. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 13208–13217
  514. Mgsvf: Multi-grained slow vs. fast framework for few-shot class-incremental learning. IEEE Transactions on Pattern Analysis and Machine Intelligence
  515. Genetic dissection of mutual interference between two consecutive learning tasks in drosophila. Elife, 12:e83516
  516. On leveraging pretrained gans for generation with limited data. In International Conference on Machine Learning, pages 11340–11351. PMLR
  517. Static-dynamic co-teaching for class-incremental 3d object detection. In Proceedings of the AAAI Conference on Artificial Intelligence, volume 36, pages 3436–3445
  518. Forward compatible few-shot class-incremental learning. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 9046–9056
  519. Few-shot class-incremental learning by sampling multi-phase tasks. IEEE Transactions on Pattern Analysis and Machine Intelligence
  520. Co-transport for class-incremental learning. In Proceedings of the ACM International Conference on Multimedia, pages 1645–1654
  521. Image de-raining via continual learning. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 4907–4916
  522. Objects as Points
  523. Class-incremental learning via dual augmentation. Advances in Neural Information Processing Systems, 34:14306–14318
  524. Prototype augmentation and self-supervision for incremental learning. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 5871–5880
  525. Self-promoted prototype refinement for few-shot class-incremental learning. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 6801–6810
  526. Self-sustaining representation expansion for non-exemplar class-incremental learning. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 9296–9305
  527. Continual prompt tuning for dialog state tracking. In Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 1124–1137
  528. Margin-Based Few-Shot Class-Incremental Learning with Class-Level Overfitting Mitigation

Show All 528