Papers
Topics
Authors
Recent
Gemini 2.5 Flash
Gemini 2.5 Flash
102 tokens/sec
GPT-4o
59 tokens/sec
Gemini 2.5 Pro Pro
43 tokens/sec
o3 Pro
6 tokens/sec
GPT-4.1 Pro
50 tokens/sec
DeepSeek R1 via Azure Pro
28 tokens/sec
2000 character limit reached

CDMAD: Class-Distribution-Mismatch-Aware Debiasing for Class-Imbalanced Semi-Supervised Learning (2403.10391v2)

Published 15 Mar 2024 in cs.CV

Abstract: Pseudo-label-based semi-supervised learning (SSL) algorithms trained on a class-imbalanced set face two cascading challenges: 1) Classifiers tend to be biased towards majority classes, and 2) Biased pseudo-labels are used for training. It is difficult to appropriately re-balance the classifiers in SSL because the class distribution of an unlabeled set is often unknown and could be mismatched with that of a labeled set. We propose a novel class-imbalanced SSL algorithm called class-distribution-mismatch-aware debiasing (CDMAD). For each iteration of training, CDMAD first assesses the classifier's biased degree towards each class by calculating the logits on an image without any patterns (e.g., solid color image), which can be considered irrelevant to the training set. CDMAD then refines biased pseudo-labels of the base SSL algorithm by ensuring the classifier's neutrality. CDMAD uses these refined pseudo-labels during the training of the base SSL algorithm to improve the quality of the representations. In the test phase, CDMAD similarly refines biased class predictions on test samples. CDMAD can be seen as an extension of post-hoc logit adjustment to address a challenge of incorporating the unknown class distribution of the unlabeled set for re-balancing the biased classifier under class distribution mismatch. CDMAD ensures Fisher consistency for the balanced error. Extensive experiments verify the effectiveness of CDMAD.

PDF HTML Abstract
Ai Sparkles Streamline Icon: https://streamlinehq.com Summarize Bookmark Chat Bubble Oval Streamline Icon: https://streamlinehq.com Chat (Pro)
Definition Search Book Streamline Icon: https://streamlinehq.com
References (68)
  1. Restricted decontamination for the imbalanced training sample problem. In Iberoamerican congress on pattern recognition, pages 424–431. Springer, 2003.
  2. Mixmatch: A holistic approach to semi-supervised learning. In Advances in Neural Information Processing Systems. Curran Associates, Inc., 2019.
  3. Remixmatch: Semi-supervised learning with distribution matching and augmentation anchoring. In International Conference on Learning Representations, 2020.
  4. Ace: Ally complementary experts for solving long-tailed recognition in one-shot. In Proceedings of the IEEE/CVF International Conference on Computer Vision, pages 112–121, 2021.
  5. Learning imbalanced datasets with label-distribution-aware margin loss. In Advances in Neural Information Processing Systems. Curran Associates, Inc., 2019.
  6. Smote: synthetic minority over-sampling technique. Journal of artificial intelligence research, 16:321–357, 2002.
  7. Softmatch: Addressing the quantity-quality tradeoff in semi-supervised learning. In Eleventh International Conference on Learning Representations. OpenReview. net, 2023.
  8. An analysis of single-layer networks in unsupervised feature learning. In Proceedings of the fourteenth international conference on artificial intelligence and statistics, pages 215–223. JMLR Workshop and Conference Proceedings, 2011.
  9. Reviving threshold-moving: a simple plug-in bagging ensemble for binary and multiclass imbalanced data. arXiv preprint arXiv:1606.08698, 2016.
  10. Randaugment: Practical automated data augmentation with a reduced search space. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, pages 702–703, 2020.
  11. Parametric contrastive learning. In Proceedings of the IEEE/CVF International Conference on Computer Vision, pages 715–724, 2021.
  12. Class-balanced loss based on effective number of samples. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 9268–9277, 2019.
  13. Improved regularization of convolutional neural networks with cutout. arXiv preprint arXiv:1708.04552, 2017.
  14. Cossl: Co-learning of representation and classifier for imbalanced semi-supervised learning. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 14574–14584, 2022.
  15. Unsupervised representation learning by predicting image rotations. In International Conference on Learning Representations, 2018.
  16. Semi-supervised learning by entropy minimization. In Advances in Neural Information Processing Systems. MIT Press, 2005.
  17. Class-imbalanced semi-supervised learning with adaptive thresholding. In International Conference on Machine Learning, pages 8082–8094. PMLR, 2022.
  18. Learning from imbalanced data. IEEE Transactions on knowledge and data engineering, 21(9):1263–1284, 2009.
  19. Deep residual learning for image recognition. In Proceedings of the IEEE conference on computer vision and pattern recognition, pages 770–778, 2016.
  20. Multilayer feedforward networks are universal approximators. Neural networks, 2(5):359–366, 1989.
  21. Learning deep representation for imbalanced classification. In Proceedings of the IEEE conference on computer vision and pattern recognition, pages 5375–5384, 2016.
  22. What makes imagenet good for transfer learning? arXiv preprint arXiv:1608.08614, 2016.
  23. Rethinking class-balanced methods for long-tailed visual recognition from a domain adaptation perspective. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 7610–7619, 2020.
  24. N JAPKOWICZ. The class imbalance problem: Significance and strategies. In Proc. 2000 International Conference on Artificial Intelligence, pages 111–117, 2000.
  25. Self-damaging contrastive learning. In International Conference on Machine Learning, pages 4927–4939. PMLR, 2021.
  26. Exploring balanced feature spaces for representation learning. In International Conference on Learning Representations, 2020a.
  27. Decoupling representation and classifier for long-tailed recognition. In International Conference on Learning Representations, 2020b.
  28. Distribution aligning refinery of pseudo-label for imbalanced semi-supervised learning. In Advances in Neural Information Processing Systems, pages 14567–14579. Curran Associates, Inc., 2020a.
  29. M2m: Imbalanced classification via major-to-minor translation. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 13896–13905, 2020b.
  30. Adam: A method for stochastic optimization. In ICLR, 2015, 2015.
  31. Unsupervised representation learning by predicting image rotations. In International conference on learning representations (ICLR), 2018.
  32. A Krizhevsky. Learning multiple layers of features from tiny images. Technical report, Department of Computer Science, University of Toronto, 2009.
  33. Addressing the curse of imbalanced training sets: one-sided selection. In Icml, page 179. Citeseer, 1997.
  34. Smoothed adaptive weighting for imbalanced semi-supervised learning: Improve reliability against unknown distribution data. In International Conference on Machine Learning, pages 11828–11843. PMLR, 2022.
  35. Unifying distribution alignment as a loss for imbalanced semi-supervised learning. In Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision, pages 5644–5653, 2023.
  36. Dong-Hyun Lee et al. Pseudo-label: The simple and efficient semi-supervised learning method for deep neural networks. In Workshop on challenges in representation learning, ICML, 2013.
  37. Abc: Auxiliary balanced classifier for class-imbalanced semi-supervised learning. Advances in Neural Information Processing Systems, 34:7082–7094, 2021.
  38. Trustworthy long-tailed classification. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 6970–6979, 2022a.
  39. Comatch: Semi-supervised learning with contrastive graph regularization. In Proceedings of the IEEE/CVF International Conference on Computer Vision, pages 9475–9484, 2021.
  40. Targeted supervised contrastive learning for long-tailed recognition. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 6918–6928, 2022b.
  41. On the statistical consistency of algorithms for binary classification under class imbalance. In International Conference on Machine Learning, pages 603–611. PMLR, 2013.
  42. Long-tail learning via logit adjustment. In International Conference on Learning Representations, 2020.
  43. Distributed representations of words and phrases and their compositionality. In Advances in Neural Information Processing Systems. Curran Associates, Inc., 2013.
  44. Virtual adversarial training: a regularization method for supervised and semi-supervised learning. IEEE transactions on pattern analysis and machine intelligence, 41(8):1979–1993, 2018.
  45. Daso: Distribution-aware semantics-oriented pseudo-label for imbalanced semi-supervised learning. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 9786–9796, 2022.
  46. Adversarial dropout for supervised and semi-supervised learning. In Proceedings of the AAAI Conference on Artificial Intelligence, 2018.
  47. Balanced meta-softmax for long-tailed visual recognition. In Advances in Neural Information Processing Systems, pages 4175–4186. Curran Associates, Inc., 2020.
  48. Imagenet large scale visual recognition challenge. International journal of computer vision, 115(3):211–252, 2015.
  49. Fixmatch: Simplifying semi-supervised learning with consistency and confidence. Advances in Neural Information Processing Systems, 33, 2020.
  50. Mean teachers are better role models: Weight-averaged consistency targets improve semi-supervised deep learning results. In Advances in Neural Information Processing Systems. Curran Associates, Inc., 2017.
  51. Laurens Van der Maaten and Geoffrey Hinton. Visualizing data using t-sne. Journal of machine learning research, 9(11), 2008.
  52. Interpolation consistency training for semi-supervised learning. In Proceedings of the Twenty-Eighth International Joint Conference on Artificial Intelligence, IJCAI-19, pages 3635–3641. International Joint Conferences on Artificial Intelligence Organization, 2019.
  53. Contrastive learning based hybrid networks for long-tailed image classification. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 943–952, 2021a.
  54. Imbalanced semi-supervised learning with bias adaptive classifier. In The Eleventh International Conference on Learning Representations, 2023a.
  55. Long-tailed recognition by routing diverse distribution-aware experts. In International Conference on Learning Representations, 2021b.
  56. Debiased learning from naturally imbalanced pseudo-labels. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 14647–14657, 2022.
  57. Freematch: Self-adaptive thresholding for semi-supervised learning. In The Eleventh International Conference on Learning Representations, 2023b.
  58. Learning to model the tail. In Advances in Neural Information Processing Systems. Curran Associates, Inc., 2017.
  59. Crest: A class-rebalancing self-training framework for imbalanced semi-supervised learning. arXiv preprint arXiv:2102.09559, 2021.
  60. Towards realistic long-tailed semi-supervised learning: Consistency is all you need. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 3469–3478, 2023.
  61. Learning from multiple experts: Self-paced knowledge distillation for long-tailed classification. In European Conference on Computer Vision, pages 247–263. Springer, 2020.
  62. Feature transfer learning for deep face recognition with under-represented data. arXiv e-prints, pages arXiv–1803, 2018.
  63. InPL: Pseudo-labeling the inliers first for imbalanced semi-supervised learning. In The Eleventh International Conference on Learning Representations, 2023.
  64. Wide residual networks. arXiv preprint arXiv:1605.07146, 2016.
  65. Flexmatch: Boosting semi-supervised learning with curriculum pseudo labeling. Advances in Neural Information Processing Systems, 34:18408–18419, 2021.
  66. Self-supervised aggregation of diverse experts for test-agnostic long-tailed recognition. Advances in Neural Information Processing Systems, 35:34077–34090, 2022.
  67. Bbn: Bilateral-branch network with cumulative learning for long-tailed visual recognition. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 9719–9728, 2020.
  68. Ding-Xuan Zhou. Universality of deep convolutional neural networks. Applied and computational harmonic analysis, 48(2):787–794, 2020.
User Edit Pencil Streamline Icon: https://streamlinehq.com
Authors (2)
  1. Hyuck Lee (3 papers)
  2. Heeyoung Kim (5 papers)
Citations (1)
View on Semantic Scholar