Skip to main content
SpringerLink
Log in

Learning to Balance Specificity and Invariance for In and Out of Domain Generalization

  • Conference paper
  • First Online:
Computer Vision – ECCV 2020 (ECCV 2020)

Part of the book series: Lecture Notes in Computer Science ((LNIP,volume 12354))

Included in the following conference series:

Abstract

We introduce Domain-specific Masks for Generalization, a model for improving both in-domain and out-of-domain generalization performance. For domain generalization, the goal is to learn from a set of source domains to produce a single model that will best generalize to an unseen target domain. As such, many prior approaches focus on learning representations which persist across all source domains with the assumption that these domain agnostic representations will generalize well. However, often individual domains contain characteristics which are unique and when leveraged can significantly aid in-domain recognition performance. To produce a model which best generalizes to both seen and unseen domains, we propose learning domain specific masks. The masks are encouraged to learn a balance of domain-invariant and domain-specific features, thus enabling a model which can benefit from the predictive power of specialized features while retaining the universal applicability of domain-invariant features. We demonstrate competitive performance compared to naive baselines and state-of-the-art methods on both PACS and DomainNet (Our code is available at https://github.com/prithv1/DMG).

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

Access this chapter

Log in via an institution
Chapter
USD 29.95
Price excludes VAT (USA)
  • Available as PDF
  • Read on any device
  • Instant download
  • Own it forever
eBook
USD 84.99
Price excludes VAT (USA)
  • Available as EPUB and PDF
  • Read on any device
  • Instant download
  • Own it forever
Softcover Book
USD 109.99
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

Notes

  1. 1.

    We experimented with learning a domain-classifier on source domains to use the predicted probabilities as weights for test-time averaging. We observed insignificant difference in out-of-domain performance but significantly worse in-domain performance, though we believe this may be dataset-specific.

  2. 2.

    Specifically, for ResNet, the domain-specific masks are trained to drop or keep specific channels in the input activations as opposed to every spatial feature in every channel in order to reduce complexity in terms of the number of mask parameters to be learnt.

  3. 3.

    For more comparisons to prior work, please refer to the supplementary material.

  4. 4.

    We report the performance for MetaReg [3] from [27] as the official PACS train-val data split changed post MetaReg [3] publication.

References

  1. Ahuja, K., Shanmugam, K., Varshney, K., Dhurandhar, A.: Invariant risk minimization games. arXiv preprint arXiv:2002.04692 (2020)

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

  3. Balaji, Y., Sankaranarayanan, S., Chellappa, R.: Metareg: towards domain generalization using meta-regularization. In: Advances in Neural Information Processing Systems. pp. 998–1008 (2018)

    Google Scholar 

  4. Bengio, Y., Léonard, N., Courville, A.: Estimating or propagating gradients through stochastic neurons for conditional computation. arXiv preprint arXiv:1308.3432 (2013)

  5. Berriel, R., et al.: Budget-aware adapters for multi-domain learning. In: Proceedings of the IEEE International Conference on Computer Vision. pp. 382–391 (2019)

    Google Scholar 

  6. Bousmalis, K., Silberman, N., Dohan, D., Erhan, D., Krishnan, D.: Unsupervised pixel-level domain adaptation with generative adversarial networks. In: The IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2017)

    Google Scholar 

  7. Bousmalis, K., Trigeorgis, G., Silberman, N., Krishnan, D., Erhan, D.: Domain separation networks. In: Advances in neural information processing systems. pp. 343–351 (2016)

    Google Scholar 

  8. Burgess, C.P., et al.: Pre: Understanding disentangling in \(\beta \)-vae. arXiv preprint arXiv:1804.03599 (2018)

  9. Chen, X., Duan, Y., Houthooft, R., Schulman, J., Sutskever, I., Abbeel, P.: Infogan: interpretable representation learning by information maximizing generative adversarial nets. In: Advances in Neural Information Processing Systems. pp. 2172–2180 (2016)

    Google Scholar 

  10. 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 

  11. Dou, Q., de Castro, D.C., Kamnitsas, K., Glocker, B.: Domain generalization via model-agnostic learning of semantic features. In: Advances in Neural Information Processing Systems. pp. 6447–6458 (2019)

    Google Scholar 

  12. Finn, C., Abbeel, P., Levine, S.: Model-agnostic meta-learning for fast adaptation of deep networks. In: Proceedings of the 34th International Conference on Machine Learning. vol. 70, pp. 1126–1135. JMLR. org (2017)

    Google Scholar 

  13. French, G., Mackiewicz, M., Fisher, M.: Self-ensembling for visual domain adaptation. In: International Conference on Learning Representations (2018), https://openreview.net/forum?id=rkpoTaxA-

  14. Ganin, Y., Ustinova, E., Ajakan, H., Germain, P., Larochelle, H., Laviolette, F., Marchand, M., Lempitsky, V.: Domain-adversarial training of neural networks. J. Mach. Learn. Res. 17(1), 2030–2096 (2016)

    MathSciNet  MATH  Google Scholar 

  15. Ghifary, M., Bastiaan Kleijn, W., Zhang, M., Balduzzi, D.: Domain generalization for object recognition with multi-task autoencoders. In: Proceedings of the IEEE international conference on computer vision. pp. 2551–2559 (2015)

    Google Scholar 

  16. Ghifary, M., Kleijn, W.B., Zhang, M., Balduzzi, D.: Domain generalization for object recognition with multi-task autoencoders. In: 2015 IEEE International Conference on Computer Vision, ICCV 2015, Santiago, Chile, December 7–13 (2015)

    Google Scholar 

  17. 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 

  18. Hoffman, J., et al.: Cycada: cycle-consistent adversarial domain adaptation. In: Proceedings of the 35th International Conference on Machine Learning, ICML 2018, Stockholmsmässan, Stockholm, Sweden, July 10–15, 2018 pp. 1994–2003 (2018)

    Google Scholar 

  19. Jaccard, P.: Etude de la distribution florale dans une portion des alpes et du jura. Bulletin de la Societe Vaudoise des Sciences Naturelles 37, 547–579 (1901). https://doi.org/10.5169/seals-266450

    Article  Google Scholar 

  20. Khosla, A., Zhou, T., Malisiewicz, T., Efros, A.A., Torralba, A.: Undoing the damage of dataset bias. In: Fitzgibbon, A., Lazebnik, S., Perona, P., Sato, Y., Schmid, C. (eds.) ECCV 2012. LNCS, vol. 7572, pp. 158–171. Springer, Heidelberg (2012). https://doi.org/10.1007/978-3-642-33718-5_12

    Chapter  Google Scholar 

  21. Kim, H., Mnih, A.: Disentangling by factorising. In: Dy, J., Krause, A. (eds.) Proceedings of the 35th International Conference on Machine Learning. Proceedings of Machine Learning Research, vol. 80, pp. 2649–2658. PMLR, Stockholmsmässan, Stockholm Sweden (2018)

    Google Scholar 

  22. Kingma, D.P., Ba, J.: Adam: A method for stochastic optimization. arXiv preprint arXiv:1412.6980 (2014)

  23. Krizhevsky, A., Sutskever, I., Hinton, G.E.: Imagenet classification with deep convolutional neural networks. In: Advances in neural information processing systems. pp. 1097–1105 (2012)

    Google Scholar 

  24. Lee, S., Kim, D., Kim, N., Jeong, S.G.: Drop to adapt: Learning discriminative features for unsupervised domain adaptation. In: Proceedings of the IEEE International Conference on Computer Vision. pp. 91–100 (2019)

    Google Scholar 

  25. Li, D., Yang, Y., Song, Y.Z., Hospedales, T.: Deeper, broader and artier domain generalization. In: International Conference on Computer Vision (2017)

    Google Scholar 

  26. Li, D., Yang, Y., Song, Y.Z., Hospedales, T.M.: Learning to generalize: Meta-learning for domain generalization. In: Thirty-Second AAAI Conference on Artificial Intelligence (2018)

    Google Scholar 

  27. Li, D., Zhang, J., Yang, Y., Liu, C., Song, Y.Z., Hospedales, T.M.: Episodic training for domain generalization. In: Proceedings of the IEEE International Conference on Computer Vision. pp. 1446–1455 (2019)

    Google Scholar 

  28. Long, M., Cao, Y., Wang, J., Jordan, M.I.: Learning transferable features with deep adaptation networks. In: Proceedings of the 32nd International Conference on Machine Learning. pp. 97–105 (2015)

    Google Scholar 

  29. Long, M., Wang, J., Jordan, M.I.: Unsupervised domain adaptation with residual transfer networks. CoRR abs/1602.04433 (2016)

  30. Long, M., Zhu, H., Wang, J., Jordan, M.I.: Deep transfer learning with joint adaptation networks. In: Precup, D., Teh, Y.W. (eds.) Proceedings of the 34th International Conference on Machine Learning, ICML 2017, Sydney, NSW, Australia, 6–11 August 2017. Proceedings of Machine Learning Research, vol. 70, pp. 2208–2217. PMLR (2017)

    Google Scholar 

  31. Mallya, A., Davis, D., Lazebnik, S.: Piggyback: Adapting a single network to multiple tasks by learning to mask weights. In: Proceedings of the European Conference on Computer Vision (ECCV). pp. 67–82 (2018)

    Google Scholar 

  32. Mallya, A., Lazebnik, S.: Packnet: Adding multiple tasks to a single network by iterative pruning. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. pp. 7765–7773 (2018)

    Google Scholar 

  33. Mancini, M., Bulò, S.R., Caputo, B., Ricci, E.: Best sources forward: domain generalization through source-specific nets. In: 2018 25th IEEE International Conference on Image Processing (ICIP). pp. 1353–1357. IEEE (2018)

    Google Scholar 

  34. Muandet, K., Balduzzi, D., Schölkopf, B.: Domain generalization via invariant feature representation. In: International Conference on Machine Learning. pp. 10–18 (2013)

    Google Scholar 

  35. Peng, X., Bai, Q., Xia, X., Huang, Z., Saenko, K., Wang, B.: Moment matching for multi-source domain adaptation. In: Proceedings of the IEEE International Conference on Computer Vision. pp. 1406–1415 (2019)

    Google Scholar 

  36. Peng, X., Huang, Z., Sun, X., Saenko, K.: Domain agnostic learning with disentangled representations. In: ICML (2019)

    Google Scholar 

  37. Rahman, M.A., Wang, Y.: Optimizing intersection-over-union in deep neural networks for image segmentation. In: Bebis, G., et al. (eds.) ISVC 2016. LNCS, vol. 10072, pp. 234–244. Springer, Cham (2016). https://doi.org/10.1007/978-3-319-50835-1_22

    Chapter  Google Scholar 

  38. Saito, K., Ushiku, Y., Harada, T., Saenko, K.: Adversarial dropout regularization. In: International Conference on Learning Representations (2018)

    Google Scholar 

  39. Saito, K., Watanabe, K., Ushiku, Y., Harada, T.: Maximum classifier discrepancy for unsupervised domain adaptation. arXiv preprint arXiv:1712.02560 (2017)

  40. Sankaranarayanan, S., Balaji, Y., Castillo, C.D., Chellappa, R.: Generate to adapt: Aligning domains using generative adversarial networks. In: The IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2018)

    Google Scholar 

  41. Savarese, P., Silva, H., Maire, M.: Winning the lottery with continuous sparsification. arXiv preprint arXiv:1912.04427 (2019)

  42. Serra, J., Suris, D., Miron, M., Karatzoglou, A.: Overcoming catastrophic forgetting with hard attention to the task. In: International Conference on Machine Learning. pp. 4548–4557 (2018)

    Google Scholar 

  43. Srivastava, N., Hinton, G., Krizhevsky, A., Sutskever, I., Salakhutdinov, R.: Dropout: a simple way to prevent neural networks from overfitting. J. Mach. Learn. Res. 15(1), 1929–1958 (2014)

    MathSciNet  MATH  Google Scholar 

  44. Tzeng, E., Hoffman, J., Saenko, K., Darrell, T.: Adversarial discriminative domain adaptation. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. pp. 7167–7176 (2017)

    Google Scholar 

  45. Venkatesh, B., Thiagarajan, J.J., Thopalli, K., Sattigeri, P.: Calibrate and prune: Improving reliability of lottery tickets through prediction calibration. arXiv preprint arXiv:2002.03875 (2020)

  46. Volpi, R., Namkoong, H., Sener, O., Duchi, J.C., Murino, V., Savarese, S.: Generalizing to unseen domains via adversarial data augmentation. In: Advances in Neural Information Processing Systems. pp. 5334–5344 (2018)

    Google Scholar 

  47. Xu, R., Chen, Z., Zuo, W., Yan, J., Lin, L.: Deep cocktail network: multi-source unsupervised domain adaptation with category shift. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. pp. 3964–3973 (2018)

    Google Scholar 

  48. Zunino, A., et al.: Explainable deep classification models for domain generalization. arXiv preprint arXiv:2003.06498 (2020)

Download references

Acknowledgements

We thank Viraj Prabhu, Daniel Bolya, Harsh Agrawal and Ramprasaath Selvaraju for fruitful discussions and feedback. This work was partially supported by DARPA award FA8750-19-1-0504.

Author information

Authors and Affiliations

  1. Georgia Institute of Technology, Atlanta, Georgia

    Prithvijit Chattopadhyay & Judy Hoffman

  2. University of Maryland, Maryland, USA

    Yogesh Balaji

Authors
  1. Prithvijit Chattopadhyay
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Yogesh Balaji
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Judy Hoffman
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Prithvijit Chattopadhyay .

Editor information

Editors and Affiliations

  1. University of Oxford, Oxford, UK

    Andrea Vedaldi

  2. Graz University of Technology, Graz, Austria

    Horst Bischof

  3. University of Freiburg, Freiburg im Breisgau, Germany

    Thomas Brox

  4. University of North Carolina at Chapel Hill, Chapel Hill, NC, USA

    Jan-Michael Frahm

1 Electronic supplementary material

Below is the link to the electronic supplementary material.

Supplementary material 1 (pdf 670 KB)

Rights and permissions

Reprints and permissions

Copyright information

© 2020 Springer Nature Switzerland AG

About this paper

Check for updates. Verify currency and authenticity via CrossMark

Cite this paper

Chattopadhyay, P., Balaji, Y., Hoffman, J. (2020). Learning to Balance Specificity and Invariance for In and Out of Domain Generalization. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, JM. (eds) Computer Vision – ECCV 2020. ECCV 2020. Lecture Notes in Computer Science(), vol 12354. Springer, Cham. https://doi.org/10.1007/978-3-030-58545-7_18

Download citation

  • DOI: https://doi.org/10.1007/978-3-030-58545-7_18

  • Published:

  • Publisher Name: Springer, Cham

  • Print ISBN: 978-3-030-58544-0

  • Online ISBN: 978-3-030-58545-7

  • eBook Packages: Computer ScienceComputer Science (R0)

Publish with us

Policies and ethics

Search

Navigation