Papers
Topics
Authors
Recent
Gemini 2.5 Flash
Gemini 2.5 Flash
139 tokens/sec
GPT-4o
7 tokens/sec
Gemini 2.5 Pro Pro
46 tokens/sec
o3 Pro
4 tokens/sec
GPT-4.1 Pro
38 tokens/sec
DeepSeek R1 via Azure Pro
28 tokens/sec
2000 character limit reached

Balanced Energy Regularization Loss for Out-of-distribution Detection (2306.10485v1)

Published 18 Jun 2023 in cs.CV, cs.AI, and cs.LG

Abstract: In the field of out-of-distribution (OOD) detection, a previous method that use auxiliary data as OOD data has shown promising performance. However, the method provides an equal loss to all auxiliary data to differentiate them from inliers. However, based on our observation, in various tasks, there is a general imbalance in the distribution of the auxiliary OOD data across classes. We propose a balanced energy regularization loss that is simple but generally effective for a variety of tasks. Our balanced energy regularization loss utilizes class-wise different prior probabilities for auxiliary data to address the class imbalance in OOD data. The main concept is to regularize auxiliary samples from majority classes, more heavily than those from minority classes. Our approach performs better for OOD detection in semantic segmentation, long-tailed image classification, and image classification than the prior energy regularization loss. Furthermore, our approach achieves state-of-the-art performance in two tasks: OOD detection in semantic segmentation and long-tailed image classification. Code is available at https://github.com/hyunjunChhoi/Balanced_Energy.

Definition Search Book Streamline Icon: https://streamlinehq.com
References (50)
  1. Discriminative out-of-distribution detection for semantic segmentation. arXiv preprint arXiv:1808.07703, 2018.
  2. Simultaneous semantic segmentation and outlier detection in presence of domain shift. In German conference on pattern recognition, pages 33–47. Springer, 2019.
  3. The fishyscapes benchmark: Measuring blind spots in semantic segmentation. International Journal of Computer Vision, 129(11):3119–3135, 2021.
  4. Learning imbalanced datasets with label-distribution-aware margin loss. Advances in neural information processing systems, 32, 2019.
  5. Entropy maximization and meta classification for out-of-distribution detection in semantic segmentation. In Proceedings of the ieee/cvf international conference on computer vision, pages 5128–5137, 2021.
  6. Atom: Robustifying out-of-distribution detection using outlier mining. In Joint European Conference on Machine Learning and Knowledge Discovery in Databases, pages 430–445. Springer, 2021.
  7. Describing textures in the wild. In Proceedings of the IEEE conference on computer vision and pattern recognition, pages 3606–3613, 2014.
  8. The cityscapes dataset for semantic urban scene understanding. In Proceedings of the IEEE conference on computer vision and pattern recognition, pages 3213–3223, 2016.
  9. Learning confidence for out-of-distribution detection in neural networks. arXiv preprint arXiv:1802.04865, 2018.
  10. Pixel-wise anomaly detection in complex driving scenes. In Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, pages 16918–16927, 2021.
  11. Learning hierarchical features for scene labeling. IEEE transactions on pattern analysis and machine intelligence, 35(8):1915–1929, 2012.
  12. Densehybrid: Hybrid anomaly detection for dense open-set recognition. arXiv preprint arXiv:2207.02606, 2022.
  13. Learning from imbalanced data. IEEE Transactions on knowledge and data engineering, 21(9):1263–1284, 2009.
  14. Deep residual learning for image recognition. In Proceedings of the IEEE conference on computer vision and pattern recognition, pages 770–778, 2016.
  15. Why relu networks yield high-confidence predictions far away from the training data and how to mitigate the problem. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 41–50, 2019.
  16. Scaling out-of-distribution detection for real-world settings. arXiv preprint arXiv:1911.11132, 2019.
  17. A baseline for detecting misclassified and out-of-distribution examples in neural networks. International Conference on Learning Representations (ICLR), 2017.
  18. Deep anomaly detection with outlier exposure. arXiv preprint arXiv:1812.04606, 2018.
  19. Standardized max logits: A simple yet effective approach for identifying unexpected road obstacles in urban-scene segmentation. In Proceedings of the IEEE/CVF International Conference on Computer Vision, pages 15425–15434, 2021.
  20. What uncertainties do we need in bayesian deep learning for computer vision? In Advances in neural information processing systems, pages 5574–5584, 2017.
  21. Learning multiple layers of features from tiny images. 2009.
  22. Imagenet classification with deep convolutional neural networks. Communications of the ACM, 60(6):84–90, 2017.
  23. Tiny imagenet visual recognition challenge. CS 231N, 7(7):3, 2015.
  24. A simple unified framework for detecting out-of-distribution samples and adversarial attacks. Advances in neural information processing systems, 31, 2018.
  25. Leveraging uncertainty information from deep neural networks for disease detection. Scientific reports, 7(1):1–14, 2017.
  26. Enhancing the reliability of out-of-distribution image detection in neural networks. arXiv preprint arXiv:1706.02690, 2017.
  27. Microsoft coco: Common objects in context. In European conference on computer vision, pages 740–755. Springer, 2014.
  28. Detecting the unexpected via image resynthesis. In Proceedings of the IEEE/CVF International Conference on Computer Vision, pages 2152–2161, 2019.
  29. Energy-based out-of-distribution detection. Advances in Neural Information Processing Systems, 33:21464–21475, 2020.
  30. Large-scale long-tailed recognition in an open world. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 2537–2546, 2019.
  31. Deep gamblers: Learning to abstain with portfolio theory. Advances in Neural Information Processing Systems, 32, 2019.
  32. Sgdr: Stochastic gradient descent with warm restarts. arXiv preprint arXiv:1608.03983, 2016.
  33. Predictive uncertainty estimation via prior networks. Advances in neural information processing systems, 31, 2018.
  34. Long-tail learning via logit adjustment. arXiv preprint arXiv:2007.07314, 2020.
  35. Self-supervised learning for generalizable out-of-distribution detection. In Proceedings of the AAAI Conference on Artificial Intelligence, volume 34, pages 5216–5223, 2020.
  36. Evaluating bayesian deep learning methods for semantic segmentation. arXiv preprint arXiv:1811.12709, 2018.
  37. Reading digits in natural images with unsupervised feature learning. 2011.
  38. Outlier exposure with confidence control for out-of-distribution detection. Neurocomputing, 441:138–150, 2021.
  39. Influence-balanced loss for imbalanced visual classification. In Proceedings of the IEEE/CVF International Conference on Computer Vision, pages 735–744, 2021.
  40. Detecting out-of-distribution examples with gram matrices. In International Conference on Machine Learning, pages 8491–8501. PMLR, 2020.
  41. Pixel-wise energy-biased abstention learning for anomaly segmentation on complex urban driving scenes. arXiv preprint arXiv:2111.12264, 2021.
  42. 80 million tiny images: A large data set for nonparametric object and scene recognition. IEEE transactions on pattern analysis and machine intelligence, 30(11):1958–1970, 2008.
  43. Partial and asymmetric contrastive learning for out-of-distribution detection in long-tailed recognition. In International Conference on Machine Learning, pages 23446–23458. PMLR, 2022.
  44. Long-tailed recognition by routing diverse distribution-aware experts. arXiv preprint arXiv:2010.01809, 2020.
  45. Open-sampling: Exploring out-of-distribution data for re-balancing long-tailed datasets. In International Conference on Machine Learning, pages 23615–23630. PMLR, 2022.
  46. Semantically coherent out-of-distribution detection. In Proceedings of the IEEE/CVF International Conference on Computer Vision, pages 8301–8309, 2021.
  47. Lsun: Construction of a large-scale image dataset using deep learning with humans in the loop. arXiv preprint arXiv:1506.03365, 2015.
  48. Wide residual networks. arXiv preprint arXiv:1605.07146, 2016.
  49. Places: A 10 million image database for scene recognition. IEEE transactions on pattern analysis and machine intelligence, 40(6):1452–1464, 2017.
  50. Semantic understanding of scenes through the ade20k dataset. International Journal of Computer Vision, 127(3):302–321, 2019.
Citations (11)
View on Semantic Scholar

Summary

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

Ai Sparkles Streamline Icon: https://streamlinehq.com Summarize Now
Github Logo Streamline Icon: https://streamlinehq.com

GitHub

  1. GitHub - hyunjunChhoi/Balanced_Energy (10 stars)