Papers
Topics
Authors
Recent
Detailed Answer
Quick Answer
Concise responses based on abstracts only
Detailed Answer
Well-researched responses based on abstracts and relevant paper content.
Custom Instructions Pro
Preferences or requirements that you'd like Emergent Mind to consider when generating responses
Gemini 2.5 Flash
Gemini 2.5 Flash 82 tok/s
Gemini 2.5 Pro 47 tok/s Pro
GPT-5 Medium 14 tok/s Pro
GPT-5 High 16 tok/s Pro
GPT-4o 117 tok/s Pro
Kimi K2 200 tok/s Pro
GPT OSS 120B 469 tok/s Pro
Claude Sonnet 4 36 tok/s Pro
2000 character limit reached

HAct: Out-of-Distribution Detection with Neural Net Activation Histograms (2309.04837v2)

Published 9 Sep 2023 in cs.LG

Abstract: We propose a simple, efficient, and accurate method for detecting out-of-distribution (OOD) data for trained neural networks. We propose a novel descriptor, HAct - activation histograms, for OOD detection, that is, probability distributions (approximated by histograms) of output values of neural network layers under the influence of incoming data. We formulate an OOD detector based on HAct descriptors. We demonstrate that HAct is significantly more accurate than state-of-the-art in OOD detection on multiple image classification benchmarks. For instance, our approach achieves a true positive rate (TPR) of 95% with only 0.03% false-positives using Resnet-50 on standard OOD benchmarks, outperforming previous state-of-the-art by 20.67% in the false positive rate (at the same TPR of 95%). The computational efficiency and the ease of implementation makes HAct suitable for online implementation in monitoring deployed neural networks in practice at scale.

Definition Search Book Streamline Icon: https://streamlinehq.com
References (28)
  1. Line: Out-of-distribution detection by leveraging important neurons, 2023.
  2. Iterative bregman projections for regularized transportation problems. SIAM Journal on Scientific Computing, 37(2):A1111–A1138, 2015.
  3. Displacement interpolation using lagrangian mass transport. In Proceedings of the 2011 SIGGRAPH Asia conference, pp.  1–12, 2011.
  4. Examples by PyTorch.org. Mnist classification example network. https://github.com/pytorch/examples/blob/main/mnist/main.py, Last accessed on 08-26-2023.
  5. Tutorials by TensorFlow.org. Cifar-10 classification example network. https://www.tensorflow.org/tutorials/images/cnn, Last accessed on 08-26-2023.
  6. Describing textures in the wild. In 2014 IEEE Conference on Computer Vision and Pattern Recognition, pp.  3606–3613, 2014. doi: 10.1109/CVPR.2014.461.
  7. Imagenet: A large-scale hierarchical image database. In 2009 IEEE Conference on Computer Vision and Pattern Recognition, pp.  248–255, 2009. doi: 10.1109/CVPR.2009.5206848.
  8. Learning confidence for out-of-distribution detection in neural networks, 2018.
  9. Extremely simple activation shaping for out-of-distribution detection. 2022. URL https://arxiv.org/abs/2209.09858.
  10. Bayesian Neural Networks: An Introduction and Survey, pp.  45–87. Springer International Publishing, Cham, 2020. ISBN 978-3-030-42553-1. doi: 10.1007/978-3-030-42553-1˙3. URL https://doi.org/10.1007/978-3-030-42553-1_3.
  11. Identity mappings in deep residual networks. In Bastian Leibe, Jiri Matas, Nicu Sebe, and Max Welling (eds.), Computer Vision – ECCV 2016, pp.  630–645, Cham, 2016. Springer International Publishing.
  12. Alex Krizhevsky. Learning multiple layers of features from tiny images.
  13. Topological uncertainty: Monitoring trained neural networks through persistence of activation graphs, 2021.
  14. Yann LeCun. The mnist database of handwritten digits. http://yann. lecun. com/exdb/mnist/, 1998.
  15. Energy-based out-of-distribution detection. Advances in neural information processing systems, 33:21464–21475, 2020.
  16. Gen: Pushing the limits of softmax-based out-of-distribution detection. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp.  23946–23955, 2023.
  17. Predictive uncertainty estimation via prior networks, 2018.
  18. Uncertainty quantification and deep ensembles. In M. Ranzato, A. Beygelzimer, Y. Dauphin, P.S. Liang, and J. Wortman Vaughan (eds.), Advances in Neural Information Processing Systems, volume 34, pp.  20063–20075. Curran Associates, Inc., 2021. URL https://proceedings.neurips.cc/paper_files/paper/2021/file/a70dc40477bc2adceef4d2c90f47eb82-Paper.pdf.
  19. Mobilenetv2: Inverted residuals and linear bottlenecks. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), June 2018.
  20. Dice: Leveraging sparsification for out-of-distribution detection. In European Conference on Computer Vision, 2022.
  21. React: Out-of-distribution detection with rectified activations, 2021.
  22. The inaturalist species classification and detection dataset. In 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp.  8769–8778, 2018. doi: 10.1109/CVPR.2018.00914.
  23. Automatic brain tumor segmentation using convolutional neural networks with test-time augmentation. In Alessandro Crimi, Spyridon Bakas, Hugo Kuijf, Farahani Keyvan, Mauricio Reyes, and Theo van Walsum (eds.), Brainlesion: Glioma, Multiple Sclerosis, Stroke and Traumatic Brain Injuries, pp.  61–72, Cham, 2019. Springer International Publishing. ISBN 978-3-030-11726-9.
  24. Fashion-mnist: a novel image dataset for benchmarking machine learning algorithms. arXiv preprint arXiv:1708.07747, 2017.
  25. Sun database: Large-scale scene recognition from abbey to zoo. In 2010 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, pp.  3485–3492, 2010. doi: 10.1109/CVPR.2010.5539970.
  26. Generalized out-of-distribution detection: A survey, 2022.
  27. Places: A 10 million image database for scene recognition. IEEE Transactions on Pattern Analysis and Machine Intelligence, 40(6):1452–1464, 2018. doi: 10.1109/TPAMI.2017.2723009.
  28. Anomaly detection with robust deep autoencoders. In Proceedings of the 23rd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, KDD ’17, pp.  665–674, New York, NY, USA, 2017. Association for Computing Machinery. ISBN 9781450348874. doi: 10.1145/3097983.3098052. URL https://doi.org/10.1145/3097983.3098052.
List To Do Tasks Checklist Streamline Icon: https://streamlinehq.com

Collections

Sign up for free to add this paper to one or more collections.

User Circle Single Streamline Icon: https://streamlinehq.com Sign Up

Summary

We haven't generated a summary for this paper yet.

Ai Sparkles Streamline Icon: https://streamlinehq.com Summarize Now
Dice Question Streamline Icon: https://streamlinehq.com

Follow-Up Questions

We haven't generated follow-up questions for this paper yet.

Ai Sparkles Streamline Icon: https://streamlinehq.com Generate Now