Skip to main content

OccamNets: Mitigating Dataset Bias by Favoring Simpler Hypotheses

  • Conference paper
  • First Online:
Computer Vision – ECCV 2022 (ECCV 2022)

Abstract

Dataset bias and spurious correlations can significantly impair generalization in deep neural networks. Many prior efforts have addressed this problem using either alternative loss functions or sampling strategies that focus on rare patterns. We propose a new direction: modifying the network architecture to impose inductive biases that make the network robust to dataset bias. Specifically, we propose OccamNets, which are biased to favor simpler solutions by design. OccamNets have two inductive biases. First, they are biased to use as little network depth as needed for an individual example. Second, they are biased toward using fewer image locations for prediction. While OccamNets are biased toward simpler hypotheses, they can learn more complex hypotheses if necessary. In experiments, OccamNets outperform or rival state-of-the-art methods run on architectures that do not incorporate these inductive biases. Furthermore, we demonstrate that when the state-of-the-art debiasing methods are combined with OccamNets (https://github.com/erobic/occam-nets-v1) results further improve.

This is a preview of subscription content, log in via an institution to check access.

Access this chapter

Chapter
USD 29.95
Price excludes VAT (USA)
  • Available as PDF
  • Read on any device
  • Instant download
  • Own it forever
eBook
USD 39.99
Price excludes VAT (USA)
  • Available as EPUB and PDF
  • Read on any device
  • Instant download
  • Own it forever
Softcover Book
USD 54.99
Price excludes VAT (USA)
  • Compact, lightweight edition
  • Dispatched in 3 to 5 business days
  • Free shipping worldwide - see info

Tax calculation will be finalised at checkout

Purchases are for personal use only

Institutional subscriptions

References

  1. Adeli, E., Zhao, Q., Pfefferbaum, A., Sullivan, E., Fei-Fei, L., Niebles, J.C., Pohl, K.: Bias-resilient neural network. arXiv abs/1910.03676 (2019)

    Google Scholar 

  2. Agrawal, A., Batra, D., Parikh, D., Kembhavi, A.: Don’t just assume; look and answer: overcoming priors for visual question answering. In: 2018 IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2018, Salt Lake City, UT, USA, 18–22 June 2018, pp. 4971–4980. IEEE Computer Society (2018). https://doi.org/10.1109/CVPR.2018.00522

  3. Ahmed, F., Bengio, Y., van Seijen, H., Courville, A.: Systematic generalisation with group invariant predictions. In: International Conference on Learning Representations (2020)

    Google Scholar 

  4. Anderson, P., et al.: Bottom-up and top-down attention for image captioning and visual question answering. In: 2018 IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2018, Salt Lake City, UT, USA, 18–22 June 2018, pp. 6077–6086. IEEE Computer Society (2018). https://doi.org/10.1109/CVPR.2018.00636

  5. Arjovsky, M., Bottou, L., Gulrajani, I., Lopez-Paz, D.: Invariant risk minimization. arXiv preprint arXiv:1907.02893 (2019)

  6. Bolukbasi, T., Chang, K., Zou, J.Y., Saligrama, V., Kalai, A.T.: Man is to computer programmer as woman is to homemaker? Debiasing word embeddings. In: Lee, D.D., Sugiyama, M., von Luxburg, U., Guyon, I., Garnett, R. (eds.) Advances in Neural Information Processing Systems 29: Annual Conference on Neural Information Processing Systems 2016, Barcelona, Spain, 5–10 December 2016, pp. 4349–4357 (2016)

    Google Scholar 

  7. Cadène, R., Dancette, C., Ben-younes, H., Cord, M., Parikh, D.: RUBi: Reducing unimodal biases for visual question answering. In: Wallach, H.M., Larochelle, H., Beygelzimer, A., d’Alché-Buc, F., Fox, E.B., Garnett, R. (eds.) Advances in Neural Information Processing Systems 32: Annual Conference on Neural Information Processing Systems 2019, NeurIPS 2019, Vancouver, BC, Canada, 8–14 December 2019, pp. 839–850 (2019)

    Google Scholar 

  8. Chawla, N.V., Bowyer, K.W., Hall, L.O., Kegelmeyer, W.P.: Smote: synthetic minority over-sampling technique. J. Artif. Intell. Res. 16, 321–357 (2002)

    Article  Google Scholar 

  9. Chen, L., Yan, X., Xiao, J., Zhang, H., Pu, S., Zhuang, Y.: Counterfactual samples synthesizing for robust visual question answering. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 10800–10809 (2020)

    Google Scholar 

  10. Chen, X., Dai, H., Li, Y., Gao, X., Song, L.: Learning to stop while learning to predict. In: International Conference on Machine Learning, pp. 1520–1530. PMLR (2020)

    Google Scholar 

  11. Choe, Y.J., Ham, J., Park, K.: An empirical study of invariant risk minimization. In: ICML 2020 Workshop on Uncertainty and Robustness in Deep Learning (2020)

    Google Scholar 

  12. Clark, C., Yatskar, M., Zettlemoyer, L.: Don’t take the easy way out: ensemble based methods for avoiding known dataset biases. In: Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP), Hong Kong, China, pp. 4069–4082. Association for Computational Linguistics (2019). https://doi.org/10.18653/v1/D19-1418

  13. Clark, C., Yatskar, M., Zettlemoyer, L.: Learning to model and ignore dataset bias with mixed capacity ensembles. In: Findings of the Association for Computational Linguistics: EMNLP 2020, pp. 3031–3045. Association for Computational Linguistics (2020). https://doi.org/10.18653/v1/2020.findings-emnlp.272

  14. Creager, E., Jacobsen, J.H., Zemel, R.: Environment inference for invariant learning. In: International Conference on Machine Learning, pp. 2189–2200. PMLR (2021)

    Google Scholar 

  15. Cui, Y., Jia, M., Lin, T., Song, Y., Belongie, S.J.: Class-balanced loss based on effective number of samples. In: IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2019, Long Beach, CA, USA, 16–20 June 2019, pp. 9268–9277. Computer Vision Foundation/IEEE (2019). https://doi.org/10.1109/CVPR.2019.00949

  16. Deng, J., Dong, W., Socher, R., Li, L.J., Li, K., Fei-Fei, L.: ImageNet: a large-scale hierarchical image database. In: 2009 IEEE conference on Computer Vision and Pattern Recognition, pp. 248–255. IEEE (2009)

    Google Scholar 

  17. Dosovitskiy, A., et al.: An image is worth 16x16 words: transformers for image recognition at scale. arXiv preprint arXiv:2010.11929 (2020)

  18. Duchi, J.C., Hashimoto, T., Namkoong, H.: Distributionally robust losses against mixture covariate shifts. Under review (2019)

    Google Scholar 

  19. Duggal, R., Freitas, S., Dhamnani, S., Horng, D., Sun, J., et al.: ELF: an early-exiting framework for long-tailed classification. arXiv preprint arXiv:2006.11979 (2020)

  20. Grand, G., Belinkov, Y.: Adversarial regularization for visual question answering: strengths, shortcomings, and side effects. In: Proceedings of the Second Workshop on Shortcomings in Vision and Language, Minneapolis, Minnesota , pp. 1–13. Association for Computational Linguistics (2019). https://doi.org/10.18653/v1/W19-1801

  21. Guo, M.H., et al.: Attention mechanisms in computer vision: a survey. arXiv preprint arXiv:2111.07624 (2021)

  22. He, H., Bai, Y., Garcia, E.A., Li, S.: ADASYN: adaptive synthetic sampling approach for imbalanced learning. In: 2008 IEEE International Joint Conference on Neural Networks (IEEE world congress on Computational Intelligence), pp. 1322–1328. IEEE (2008)

    Google Scholar 

  23. He, H., Garcia, E.A.: Learning from imbalanced data. IEEE Trans. Knowl. Data Eng. 21(9), 1263–1284 (2009)

    Article  Google Scholar 

  24. He, K., Gkioxari, G., Dollár, P., Girshick, R.: Mask R-CNN. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 2961–2969 (2017)

    Google Scholar 

  25. He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 770–778 (2016)

    Google Scholar 

  26. Hettinger, C., Christensen, T., Ehlert, B., Humpherys, J., Jarvis, T., Wade, S.: Forward thinking: building and training neural networks one layer at a time. arXiv preprint arXiv:1706.02480 (2017)

  27. Hooker, S., Moorosi, N., Clark, G., Bengio, S., Denton, E.: Characterising bias in compressed models. arXiv preprint arXiv:2010.03058 (2020)

  28. Howard, A., et al.: Searching for mobileNetV3. In: Proceedings of the IEEE/CVF International Conference on Computer Vision, pp. 1314–1324 (2019)

    Google Scholar 

  29. Howard, A.G., et al.: MobileNets: efficient convolutional neural networks for mobile vision applications. arXiv preprint arXiv:1704.04861 (2017)

  30. Hu, J., Shen, L., Albanie, S., Sun, G., Vedaldi, A.: Gather-excite: exploiting feature context in convolutional neural networks. In: Advances in Neural Information Processing Systems 31 (2018)

    Google Scholar 

  31. Hu, T.K., Chen, T., Wang, H., Wang, Z.: Triple wins: boosting accuracy, robustness and efficiency together by enabling input-adaptive inference. arXiv preprint arXiv:2002.10025 (2020)

  32. Huang, G., Liu, Z., Van Der Maaten, L., Weinberger, K.Q.: Densely connected convolutional networks. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 4700–4708 (2017)

    Google Scholar 

  33. Jaderberg, M., Simonyan, K., Zisserman, A., et al.: Spatial transformer networks. In: Advances in Neural Information Processing Systems, vol. 28 (2015)

    Google Scholar 

  34. Kim, B., Kim, H., Kim, K., Kim, S., Kim, J.: Learning not to learn: training deep neural networks with biased data. In: IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2019, Long Beach, CA, USA, 16–20 June 2019, pp. 9012–9020. Computer Vision Foundation/IEEE (2019). https://doi.org/10.1109/CVPR.2019.00922

  35. Kim, E., Lee, J., Choo, J.: BiaSwap: removing dataset bias with bias-tailored swapping augmentation. In: Proceedings of the IEEE/CVF International Conference on Computer Vision, pp. 14992–15001 (2021)

    Google Scholar 

  36. Krueger, D., et al.: Out-of-distribution generalization via risk extrapolation (REx). In: International Conference on Machine Learning. pp, 5815–5826. PMLR (2021)

    Google Scholar 

  37. Lee, C.Y., Gallagher, P.W., Tu, Z.: Generalizing pooling functions in convolutional neural networks: mixed, gated, and tree. In: Artificial Intelligence and Statistics, pp. 464–472. PMLR (2016)

    Google Scholar 

  38. Lee, C.Y., Xie, S., Gallagher, P., Zhang, Z., Tu, Z.: Deeply-supervised nets. In: Artificial Intelligence and Statistics, pp. 562–570. PMLR (2015)

    Google Scholar 

  39. Lee, Y., Yao, H., Finn, C.: Diversify and disambiguate: learning from underspecified data. arXiv preprint arXiv:2202.03418 (2022)

  40. Li, Y., Vasconcelos, N.: REPAIR: removing representation bias by dataset resampling. In: IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2019, Long Beach, CA, USA, 16–20 June 2019, pp. 9572–9581. Computer Vision Foundation/IEEE (2019). https://doi.org/10.1109/CVPR.2019.00980

  41. Lin, T.-Y., Maire, M., Belongie, S., Hays, J., Perona, P., Ramanan, D., Dollár, P., Zitnick, C.L.: Microsoft COCO: common objects in context. In: Fleet, D., Pajdla, T., Schiele, B., Tuytelaars, T. (eds.) ECCV 2014. LNCS, vol. 8693, pp. 740–755. Springer, Cham (2014). https://doi.org/10.1007/978-3-319-10602-1_48

    Chapter  Google Scholar 

  42. Liu, E.Z., et al.: Just train twice: Improving group robustness without training group information. In: International Conference on Machine Learning, pp. 6781–6792. PMLR (2021)

    Google Scholar 

  43. Liu, Z., Lin, Y., Cao, Y., Hu, H., Wei, Y., Zhang, Z., Lin, S., Guo, B.: Swin transformer: hierarchical vision transformer using shifted windows. In: Proceedings of the IEEE/CVF International Conference on Computer Vision, pp. 10012–10022 (2021)

    Google Scholar 

  44. Long, J., Shelhamer, E., Darrell, T.: Fully convolutional networks for semantic segmentation. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 3431–3440 (2015)

    Google Scholar 

  45. Mehrabi, N., Morstatter, F., Saxena, N., Lerman, K., Galstyan, A.: A survey on bias and fairness in machine learning. ACM Comput. Surv. (CSUR) 54(6), 1–35 (2021)

    Article  Google Scholar 

  46. Mostafa, H., Ramesh, V., Cauwenberghs, G.: Deep supervised learning using local errors. Front. Neurosci. 12, 608 (2018)

    Google Scholar 

  47. Nam, J., Cha, H., Ahn, S., Lee, J., Shin, J.: Learning from failure: training debiased classifier from biased classifier. In: Advances in Neural Information Processing Systems (2020)

    Google Scholar 

  48. Namkoong, H., Duchi, J.C.: Stochastic gradient methods for distributionally robust optimization with F-divergences. In: Lee, D.D., Sugiyama, M., von Luxburg, U., Guyon, I., Garnett, R. (eds.) Advances in Neural Information Processing Systems 29: Annual Conference on Neural Information Processing Systems 2016, Barcelona, Spain, 5–10 December 2016, pp. 2208–2216 (2016)

    Google Scholar 

  49. Nøkland, A.: Direct feedback alignment provides learning in deep neural networks. In: Advances in Neural Information Processing Systems, vol. 29 (2016)

    Google Scholar 

  50. Nøkland, A., Eidnes, L.H.: Training neural networks with local error signals. In: International Conference on Machine Learning, pp. 4839–4850. PMLR (2019)

    Google Scholar 

  51. Pezeshki, M., Kaba, S.O., Bengio, Y., Courville, A., Precup, D., Lajoie, G.: Gradient starvation: a learning proclivity in neural networks. arXiv preprint arXiv:2011.09468 (2020)

  52. Rahimian, H., Mehrotra, S.: Distributionally robust optimization: a review. arXiv preprint arXiv:1908.05659 (2019)

  53. Ramakrishnan, S., Agrawal, A., Lee, S.: Overcoming language priors in visual question answering with adversarial regularization. In: Bengio, S., Wallach, H.M., Larochelle, H., Grauman, K., Cesa-Bianchi, N., Garnett, R. (eds.) Advances in Neural Information Processing Systems 31: Annual Conference on Neural Information Processing Systems 2018, NeurIPS 2018, Montréal, Canada, 3–8 December 2018, pp. 1548–1558 (2018)

    Google Scholar 

  54. Ronneberger, O., Fischer, P., Brox, T.: U-Net: convolutional networks for biomedical image segmentation. In: Navab, N., Hornegger, J., Wells, W.M., Frangi, A.F. (eds.) MICCAI 2015. LNCS, vol. 9351, pp. 234–241. Springer, Cham (2015). https://doi.org/10.1007/978-3-319-24574-4_28

    Chapter  Google Scholar 

  55. Sagawa, S., Koh, P.W., Hashimoto, T.B., Liang, P.: Distributionally robust neural networks for group shifts: on the importance of regularization for worst-case generalization. CoRR abs/1911.08731 (2019), https://arxiv.org/abs/1911.08731

  56. Sagawa, S., Koh, P.W., Hashimoto, T.B., Liang, P.: Distributionally robust neural networks for group shifts: on the importance of regularization for worst-case generalization. arXiv preprint arXiv:1911.08731 (2019)

  57. Sagawa, S., Raghunathan, A., Koh, P.W., Liang, P.: An investigation of why overparameterization exacerbates spurious correlations. In: Proceedings of the 37th International Conference on Machine Learning, ICML 2020, 13–18 July 2020, Virtual Event. Proceedings of Machine Learning Research, vol. 119, pp. 8346–8356. PMLR (2020)

    Google Scholar 

  58. Sanh, V., Wolf, T., Belinkov, Y., Rush, A.M.: Learning from others’ mistakes: avoiding dataset biases without modeling them. arXiv preprint arXiv:2012.01300 (2020)

  59. Scardapane, S., Scarpiniti, M., Baccarelli, E., Uncini, A.: Why should we add early exits to neural networks? Cognit. Comput. 12(5), 954–966 (2020)

    Article  Google Scholar 

  60. Selvaraju, R.R., Cogswell, M., Das, A., Vedantam, R., Parikh, D., Batra, D.: Grad-CAM: visual explanations from deep networks via gradient-based localization. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 618–626 (2017)

    Google Scholar 

  61. Shah, H., Tamuly, K., Raghunathan, A., Jain, P., Netrapalli, P.: The pitfalls of simplicity bias in neural networks. In: Advances in Neural Information Processing Systems, vol. 33 (2020)

    Google Scholar 

  62. Shrestha, R., Kafle, K., Kanan, C.: An investigation of critical issues in bias mitigation techniques. In: Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision, pp. 1943–1954 (2022)

    Google Scholar 

  63. Singh, K.K., Mahajan, D., Grauman, K., Lee, Y.J., Feiszli, M., Ghadiyaram, D.: Don’t judge an object by its context: learning to overcome contextual bias. In: 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2020, Seattle, WA, USA, 13–19 June 2020, pp. 11067–11075. IEEE (2020). https://doi.org/10.1109/CVPR42600.2020.01108

  64. Szegedy, C., Liu, W., Jia, Y., Sermanet, P., Reed, S., Anguelov, D., Erhan, D., Vanhoucke, V., Rabinovich, A.: Going deeper with convolutions. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 1–9 (2015)

    Google Scholar 

  65. Tan, M., Le, Q.: EfficientNet: rethinking model scaling for convolutional neural networks. In: International Conference on Machine Learning, pp. 6105–6114. PMLR (2019)

    Google Scholar 

  66. Teerapittayanon, S., McDanel, B., Kung, H.T.: BranchyNet: fast inference via early exiting from deep neural networks. In: 2016 23rd International Conference on Pattern Recognition (ICPR), pp. 2464–2469. IEEE (2016)

    Google Scholar 

  67. Teney, D., Abbasnejad, E., van den Hengel, A.: Unshuffling data for improved generalization. arXiv preprint arXiv:2002.11894 (2020)

  68. Teney, D., Abbasnejad, E., Lucey, S., van den Hengel, A.: Evading the simplicity bias: training a diverse set of models discovers solutions with superior ood generalization. arXiv preprint arXiv:2105.05612 (2021)

  69. Tolstikhin, I.O., Houlsby, N., Kolesnikov, A., Beyer, L., Zhai, X., Unterthiner, T., Yung, J., Steiner, A., Keysers, D., Uszkoreit, J., et al.: Mlp-mixer: An all-mlp architecture for vision. Advances in Neural Information Processing Systems 34 (2021)

    Google Scholar 

  70. Torralba, A., Efros, A.A.: Unbiased look at dataset bias. In: The 24th IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2011, Colorado Springs, CO, USA, 20–25 June 2011. pp. 1521–1528. IEEE Computer Society (2011). https://doi.org/10.1109/CVPR.2011.5995347

  71. Utama, P.A., Moosavi, N.S., Gurevych, I.: Towards debiasing NLU models from unknown biases. In: Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP), pp. 7597–7610. Association for Computational Linguistics (2020). https://doi.org/10.18653/v1/2020.emnlp-main.613. https://www.aclweb.org/anthology/2020.emnlp-main.613

  72. Venkataramani, S., Raghunathan, A., Liu, J., Shoaib, M.: Scalable-effort classifiers for energy-efficient machine learning. In: Proceedings of the 52nd Annual Design Automation Conference. pp. 1–6 (2015)

    Google Scholar 

  73. Wołczyk, M., et al.:: Zero time waste: recycling predictions in early exit neural networks. In: Advances in Neural Information Processing Systems 34 (2021)

    Google Scholar 

  74. Xu, K., Ba, J., et al.: Show, attend and tell: neural image caption generation with visual attention. In: International conference on Machine Learning, pp. 2048–2057. PMLR (2015)

    Google Scholar 

  75. Yu, W., et al.: Metaformer is actually what you need for vision. arXiv preprint arXiv:2111.11418 (2021)

  76. Zhang, B.H., Lemoine, B., Mitchell, M.: Mitigating unwanted biases with adversarial learning. In: Proceedings of the 2018 AAAI/ACM Conference on AI, Ethics, and Society, pp. 335–340 (2018)

    Google Scholar 

  77. Zhou, B., Lapedriza, A., Khosla, A., Oliva, A., Torralba, A.: Places: A 10 million image database for scene recognition. IEEE T. Pattern Anal. Mach. Intell. 40(6), 1452–1464 (2017)

    Article  Google Scholar 

  78. Zhou, W., et al.: BERT loses patience: fast and robust inference with early exit. In: Advances in Neural Information Processing Systems, vol. 33, pp. 18330–18341 (2020)

    Google Scholar 

Download references

Acknowledgments

This work was supported in part by NSF awards #1909696 and #2047556. The views and conclusions contained herein are those of the authors and should not be interpreted as representing the official policies or endorsements of any sponsor.

Author information

Authors and Affiliations

Authors

Corresponding author

Correspondence to Robik Shrestha .

Editor information

Editors and Affiliations

1 Electronic supplementary material

Below is the link to the electronic supplementary material.

Supplementary material 1 (zip 864 KB)

Rights and permissions

Reprints and permissions

Copyright information

© 2022 The Author(s), under exclusive license to Springer Nature Switzerland AG

About this paper

Check for updates. Verify currency and authenticity via CrossMark

Cite this paper

Shrestha, R., Kafle, K., Kanan, C. (2022). OccamNets: Mitigating Dataset Bias by Favoring Simpler Hypotheses. In: Avidan, S., Brostow, G., Cissé, M., Farinella, G.M., Hassner, T. (eds) Computer Vision – ECCV 2022. ECCV 2022. Lecture Notes in Computer Science, vol 13680. Springer, Cham. https://doi.org/10.1007/978-3-031-20044-1_40

Download citation

  • DOI: https://doi.org/10.1007/978-3-031-20044-1_40

  • Published:

  • Publisher Name: Springer, Cham

  • Print ISBN: 978-3-031-20043-4

  • Online ISBN: 978-3-031-20044-1

  • eBook Packages: Computer ScienceComputer Science (R0)

Publish with us

Policies and ethics