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

Hybrid Sample Synthesis-based Debiasing of Classifier in Limited Data Setting (2312.08288v2)

Published 13 Dec 2023 in cs.CV and cs.LG

Abstract: Deep learning models are known to suffer from the problem of bias, and researchers have been exploring methods to address this issue. However, most of these methods require prior knowledge of the bias and are not always practical. In this paper, we focus on a more practical setting with no prior information about the bias. Generally, in this setting, there are a large number of bias-aligned samples that cause the model to produce biased predictions and a few bias-conflicting samples that do not conform to the bias. If the training data is limited, the influence of the bias-aligned samples may become even stronger on the model predictions, and we experimentally demonstrate that existing debiasing techniques suffer severely in such cases. In this paper, we examine the effects of unknown bias in small dataset regimes and present a novel approach to mitigate this issue. The proposed approach directly addresses the issue of the extremely low occurrence of bias-conflicting samples in limited data settings through the synthesis of hybrid samples that can be used to reduce the effect of bias. We perform extensive experiments on several benchmark datasets and experimentally demonstrate the effectiveness of our proposed approach in addressing any unknown bias in the presence of limited data. Specifically, our approach outperforms the vanilla, LfF, LDD, and DebiAN debiasing methods by absolute margins of 10.39%, 9.08%, 8.07%, and 9.67% when only 10% of the Corrupted CIFAR-10 Type 1 dataset is available with a bias-conflicting sample ratio of 0.05.

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 (26)
  1. Learning de-biased representations with biased representations. In International Conference on Machine Learning (ICML), 2020.
  2. Evidential deep learning for open set action recognition. In Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV), pages 13349–13358, October 2021.
  3. Learning to split for automatic bias detection. arXiv preprint arXiv:2204.13749, 2022.
  4. Learning stable classifiers by transferring unstable features. In International Conference on Machine Learning, pages 1483–1507. PMLR, 2022.
  5. Don’t take the easy way out: Ensemble based methods for avoiding known dataset biases, 2019.
  6. Latent adversarial debiasing: Mitigating collider bias in deep neural networks. arXiv preprint arXiv:2011.11486, 2020.
  7. Li Deng. The mnist database of handwritten digit images for machine learning research [best of the web]. IEEE signal processing magazine, 29(6):141–142, 2012.
  8. Shortcut learning in deep neural networks. Nature Machine Intelligence, 2(11):665–673, 2020.
  9. Deep residual learning for image recognition. In 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pages 770–778, 2016.
  10. Benchmarking neural network robustness to common corruptions and perturbations. arXiv preprint arXiv:1903.12261, 2019.
  11. Self-challenging improves cross-domain generalization. In Computer Vision–ECCV 2020: 16th European Conference, Glasgow, UK, August 23–28, 2020, Proceedings, Part II 16, pages 124–140. Springer, 2020.
  12. A style-based generator architecture for generative adversarial networks. In 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pages 4396–4405, 2019.
  13. A style-based generator architecture for generative adversarial networks. In Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, pages 4401–4410, 2019.
  14. Learning not to learn: Training deep neural networks with biased data. In The IEEE Conference on Computer Vision and Pattern Recognition (CVPR), June 2019.
  15. Biaswap: Removing dataset bias with bias-tailored swapping augmentation. In Proceedings of the IEEE/CVF International Conference on Computer Vision, pages 14992–15001, 2021.
  16. Adam: A method for stochastic optimization. arXiv preprint arXiv:1412.6980, 2014.
  17. Learning multiple layers of features from tiny images. 2009.
  18. Learning debiased representation via disentangled feature augmentation. In Advances in Neural Information Processing Systems, volume 34, pages 25123–25133, 2021.
  19. Discover and Mitigate Unknown Biases with Debiasing Alternate Networks. In The European Conference on Computer Vision (ECCV), 2022.
  20. Protected attribute guided representation learning for bias mitigation. Knowledge-Based Systems, 244:108449, 2022.
  21. Learning from failure: Training debiased classifier from biased classifier. In Advances in Neural Information Processing Systems, 2020.
  22. Automatic differentiation in pytorch, 2017.
  23. ”why should i trust you?”: Explaining the predictions of any classifier. In Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, KDD ’16, page 1135–1144, New York, NY, USA, 2016. Association for Computing Machinery.
  24. Learning robust representations by projecting superficial statistics out. In International Conference on Learning Representations, 2019.
  25. Generalized cross entropy loss for training deep neural networks with noisy labels. Advances in neural information processing systems, 31, 2018.
  26. Object recognition with and without objects. arXiv preprint arXiv:1611.06596, 2016.
User Edit Pencil Streamline Icon: https://streamlinehq.com
Authors (2)
  1. Piyush Arora (2 papers)
  2. Pratik Mazumder (13 papers)