Class-Incremental Learning for Multi-Label Audio Classification (2401.04447v1)
Abstract: In this paper, we propose a method for class-incremental learning of potentially overlapping sounds for solving a sequence of multi-label audio classification tasks. We design an incremental learner that learns new classes independently of the old classes. To preserve knowledge about the old classes, we propose a cosine similarity-based distillation loss that minimizes discrepancy in the feature representations of subsequent learners, and use it along with a Kullback-Leibler divergence-based distillation loss that minimizes discrepancy in their respective outputs. Experiments are performed on a dataset with 50 sound classes, with an initial classification task containing 30 base classes and 4 incremental phases of 5 classes each. After each phase, the system is tested for multi-label classification with the entire set of classes learned so far. The proposed method obtains an average F1-score of 40.9% over the five phases, ranging from 45.2% in phase 0 on 30 classes, to 36.3% in phase 4 on 50 classes. Average performance degradation over incremental phases is only 0.7 percentage points from the initial F1-score of 45.2%.
- “Continual lifelong learning with neural networks: A review,” Neural networks, vol. 113, pp. 54–71, 2019.
- “icarl: Incremental classifier and representation learning,” in Proceedings of the IEEE conference on Computer Vision and Pattern Recognition, 2017, pp. 2001–2010.
- Gido M Van de Ven and Andreas S Tolias, “Three scenarios for continual learning,” in Continual Learning Workshop NeurIPS, 2018.
- “Learning without forgetting,” IEEE Transactions on pattern analysis and machine intelligence, vol. 40, no. 12, pp. 2935–2947, 2017.
- “Gradient episodic memory for continual learning,” Advances in neural information processing systems, vol. 30, 2017.
- “Adaptive aggregation networks for class-incremental learning,” in Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2021, pp. 2544–2553.
- “Essentials for class incremental learning,” in Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2021, pp. 3513–3522.
- “Gcr: Gradient coreset based replay buffer selection for continual learning,” in Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2022, pp. 99–108.
- “Self-distilled knowledge delegator for exemplar-free class incremental learning,” in International Joint Conference on Neural Networks (IJCNN). IEEE, 2022, pp. 1–8.
- “A closer look at rehearsal-free continual learning,” in Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2023, pp. 2409–2419.
- “An incremental class-learning approach with acoustic novelty detection for acoustic event recognition,” Sensors, vol. 21, no. 19, pp. 6622, 2021.
- “Learning representations for new sound classes with continual self-supervised learning,” IEEE Signal Processing Letters, vol. 29, pp. 2607–2611, 2022.
- “Few-shot continual learning for audio classification,” in IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). IEEE, 2021, pp. 321–325.
- “Incremental learning of acoustic scenes and sound events,” in Proceedings of the 8th Workshop on Detection and Classification of Acoustic Scenes and Events (DCASE), 2023, pp. 141–145.
- “Learning a unified classifier incrementally via rebalancing,” in Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2019, pp. 831–839.
- “Class-incremental learning by knowledge distillation with adaptive feature consolidation,” in Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, 2022, pp. 16071–16080.
- “The benefit of temporally-strong labels in audio event classification,” in IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). IEEE, 2021, pp. 366–370.
- “PANNs: Large-scale pretrained audio neural networks for audio pattern recognition,” IEEE/ACM Transactions on Audio, Speech, and Language Processing, vol. 28, pp. 2880–2894, 2020.
- “SGDR: Stochastic gradient descent with warm restarts,” in International Conference on Learning Representations (ICLR), 2017.
Collections
Sign up for free to add this paper to one or more collections.
Paper Prompts
Sign up for free to create and run prompts on this paper using GPT-5.