Advertisement

Learning to Generate Novel Domains for Domain Generalization

Conference paper
  • 976 Downloads
Part of the Lecture Notes in Computer Science book series (LNCS, volume 12361)

Abstract

This paper focuses on domain generalization (DG), the task of learning from multiple source domains a model that generalizes well to unseen domains. A main challenge for DG is that the available source domains often exhibit limited diversity, hampering the model’s ability to learn to generalize. We therefore employ a data generator to synthesize data from pseudo-novel domains to augment the source domains. This explicitly increases the diversity of available training domains and leads to a more generalizable model. To train the generator, we model the distribution divergence between source and synthesized pseudo-novel domains using optimal transport, and maximize the divergence. To ensure that semantics are preserved in the synthesized data, we further impose cycle-consistency and classification losses on the generator. Our method, L2A-OT (Learning to Augment by Optimal Transport) outperforms current state-of-the-art DG methods on four benchmark datasets.

Supplementary material

504471_1_En_33_MOESM1_ESM.pdf (131 kb)
Supplementary material 1 (pdf 130 KB)

References

  1. 1.
    Arjovsky, M., Chintala, S., Bottou, L.: Wasserstein generative adversarial networks. In: ICML (2017)Google Scholar
  2. 2.
    Balaji, Y., Sankaranarayanan, S., Chellappa, R.: MetaReg: towards domain generalization using meta-regularization. In: NeurIPS (2018)Google Scholar
  3. 3.
    Bellemare, M.G., et al.: The cramer distance as a solution to biased wasserstein gradients. arXiv preprint arXiv:1705.10743 (2017)
  4. 4.
    Ben-David, Shai., Blitzer, John., Crammer, Koby., Kulesza, Alex., Pereira, Fernando, Vaughan, Jennifer Wortman: A theory of learning from different domains. Mach. Learn. 79(1), 151–175 (2009).  https://doi.org/10.1007/s10994-009-5152-4MathSciNetCrossRefGoogle Scholar
  5. 5.
    Carlucci, F.M., D’Innocente, A., Bucci, S., Caputo, B., Tommasi, T.: Domain generalization by solving jigsaw puzzles. In: CVPR (2019)Google Scholar
  6. 6.
    Choi, Y., Choi, M., Kim, M., Ha, J.W., Kim, S., Choo, J.: StarGAN: unified generative adversarial networks for multi-domain image-to-image translation. In: CVPR (2018)Google Scholar
  7. 7.
    Cuturi, M.: Sinkhorn distances: lightspeed computation of optimal transport. In: NeurIPS (2013)Google Scholar
  8. 8.
    Deng, J., Dong, W., Socher, R., Li, L.J., Li, K., Fei-Fei, L.: ImageNet: a large-scale hierarchical image database. In: CVPR (2009)Google Scholar
  9. 9.
    D’Innocente, A., Caputo, B.: Domain generalization with domain-specific aggregation modules. In: GCPR (2018)Google Scholar
  10. 10.
    Dou, Q., Castro, D.C., Kamnitsas, K., Glocker, B.: Domain generalization via model-agnostic learning of semantic features. In: NeurIPS (2019)Google Scholar
  11. 11.
    Gan, C., Yang, T., Gong, B.: Learning attributes equals multi-source domain generalization. In: CVPR (2016)Google Scholar
  12. 12.
    Ganin, Y., Lempitsky, V.S.: Unsupervised domain adaptation by backpropagation. In: ICML (2015)Google Scholar
  13. 13.
    Ganin, Y., et al.: Domain-adversarial training of neural networks. JMLR 17(1), 2030–2096 (2016)MathSciNetGoogle Scholar
  14. 14.
    Genevay, A., Peyré, G., Cuturi, M.: Learning generative models with sinkhorn divergences. In: AISTATS (2018)Google Scholar
  15. 15.
    Ghifary, M., Balduzzi, D., Kleijn, W.B., Zhang, M.: Scatter component analysis: a unified framework for domain adaptation and domain generalization. TPAMI 39(7), 1414–1430 (2017)CrossRefGoogle Scholar
  16. 16.
    Ghifary, M., Kleijn, W.B., Zhang, M., Balduzzi, D.: Domain generalization for object recognition with multi-task autoencoders. In: ICCV (2015)Google Scholar
  17. 17.
    Goodfellow, I., et al.: Generative adversarial nets. In: NeurIPS (2014)Google Scholar
  18. 18.
    Goodfellow, I.J., Shlens, J., Szegedy, C.: Explaining and harnessing adversarial examples. In: ICLR (2015)Google Scholar
  19. 19.
    He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: CVPR (2016)Google Scholar
  20. 20.
    Hoffman, J., et al.: CyCADA: cycle-consistent adversarial domain adaptation. In: ICML (2018)Google Scholar
  21. 21.
    Hospedales, T., Antoniou, A., Micaelli, P., Storkey, A.: Meta-learning in neural networks: a survey. arXiv preprint arXiv:2004.05439 (2020)
  22. 22.
    Jin, X., Lan, C., Zeng, W., Chen, Z., Zhang, L.: Style normalization and restitution for generalizable person re-identification. In: CVPR (2020)Google Scholar
  23. 23.
    Kingma, D.P., Ba, J.: Adam: a method for stochastic optimization. In: ICLR (2014)Google Scholar
  24. 24.
    LeCun, Y., Bottou, L., Bengio, Y., Haffner, P.: Gradient-based learning applied to document recognition. Proc. IEEE 86(11), 2278–2324 (1998)CrossRefGoogle Scholar
  25. 25.
    Li, D., Yang, Y., Song, Y.Z., Hospedales, T.M.: Deeper, broader and artier domain generalization. In: ICCV (2017)Google Scholar
  26. 26.
    Li, D., Yang, Y., Song, Y.Z., Hospedales, T.M.: Learning to generalize: meta-learning for domain generalization. In: AAAI (2018)Google Scholar
  27. 27.
    Li, D., Zhang, J., Yang, Y., Liu, C., Song, Y.Z., Hospedales, T.M.: Episodic training for domain generalization. In: ICCV (2019)Google Scholar
  28. 28.
    Li, H., Jialin Pan, S., Wang, S., Kot, A.C.: Domain generalization with adversarial feature learning. In: CVPR (2018)Google Scholar
  29. 29.
    Li, Y., Tiana, X., Gong, M., Liu, Y., Liu, T., Zhang, K., Tao, D.: Deep domain generalization via conditional invariant adversarial networks. In: ECCV (2018)Google Scholar
  30. 30.
    Li, Y., Fang, C., Yang, J., Wang, Z., Lu, X., Yang, M.H.: Diversified texture synthesis with feed-forward networks. In: CVPR (2017)Google Scholar
  31. 31.
    Li, Y., Yang, Y., Zhou, W., Hospedales, T.: Feature-critic networks for heterogeneous domain generalization. In: ICML (2019)Google Scholar
  32. 32.
    Liu, J., Zha, Z.J., Chen, D., Hong, R., Wang, M.: Adaptive transfer network for cross-domain person re-identification. In: CVPR (2019)Google Scholar
  33. 33.
    Long, M., Cao, Y., Wang, J., Jordan, M.I.: Learning transferable features with deep adaptation networks. In: ICML (2015)Google Scholar
  34. 34.
    Maaten, L.V.D., Hinton, G.: Visualizing data using t-SNE. JMLR 9, 2579–2605 (2008)zbMATHGoogle Scholar
  35. 35.
    Moreno-Torres, J.G., Raeder, T., Alaiz-RodríGuez, R., Chawla, N.V., Herrera, F.: A unifying view on dataset shift in classification. PR 45(1), 521–530 (2012)Google Scholar
  36. 36.
    Motiian, S., Piccirilli, M., Adjeroh, D.A., Doretto, G.: Unified deep supervised domain adaptation and generalization. In: ICCV (2017)Google Scholar
  37. 37.
    Muandet, K., Balduzzi, D., Scholkopf, B.: Domain generalization via invariant feature representation. In: ICML (2013)Google Scholar
  38. 38.
    Netzer, Y., Wang, T., Coates, A., Bissacco, A., Wu, B., Ng, A.Y.: Reading digits in natural images with unsupervised feature learning. In: NeurIPS-W (2011)Google Scholar
  39. 39.
    Noroozi, M., Favaro, P.: Unsupervised learning of visual representations by solving jigsaw puzzles. In: ECCV (2016)Google Scholar
  40. 40.
    Peng, X., Bai, Q., Xia, X., Huang, Z., Saenko, K., Wang, B.: Moment matching for multi-source domain adaptation. In: ICCV (2019)Google Scholar
  41. 41.
    Peyré, G., Cuturi, M., et al.: Computational optimal transport. Found. Trends Mach. Learn. 11(5–6), 355–607 (2019)CrossRefGoogle Scholar
  42. 42.
    Prakash, A., et al.: Structured domain randomization: bridging the reality gap by context-aware synthetic data. In: ICRA (2019)Google Scholar
  43. 43.
    Ristani, E., Solera, F., Zou, R.S., Cucchiara, R., Tomasi, C.: Performance measures and a data set for multi-target, multi-camera tracking. In: ECCV-W (2016)Google Scholar
  44. 44.
    Saito, K., Kim, D., Sclaroff, S., Darrell, T., Saenko, K.: Semi-supervised domain adaptation via minimax entropy. In: ICCV (2019)Google Scholar
  45. 45.
    Salimans, T., Zhang, H., Radford, A., Metaxas, D.: Improving GANs using optimal transport. In: ICLR (2018)Google Scholar
  46. 46.
    Shaham, T.R., Dekel, T., Michaeli, T.: Singan: Learning a generative model from a single natural image. In: ICCV (2019)Google Scholar
  47. 47.
    Shankar, S., Piratla, V., Chakrabarti, S., Chaudhuri, S., Jyothi, P., Sarawagi, S.: Generalizing across domains via cross-gradient training. In: ICLR (2018)Google Scholar
  48. 48.
    Szegedy, C., et al.: Intriguing properties of neural networks. In: ICLR (2014)Google Scholar
  49. 49.
    Tobin, J., Fong, R., Ray, A., Schneider, J., Zaremba, W., Abbeel, P.: Domain randomization for transferring deep neural networks from simulation to the real world. In: IROS (2017)Google Scholar
  50. 50.
    Tzeng, E., Hoffman, J., Saenko, K., Darrell, T.: Adversarial discriminative domain adaptation. In: CVPR (2017)Google Scholar
  51. 51.
    Venkateswara, H., Eusebio, J., Chakraborty, S., Panchanathan, S.: Deep hashing network for unsupervised domain adaptation. In: CVPR (2017)Google Scholar
  52. 52.
    Volpi, R., Namkoong, H., Sener, O., Duchi, J., Murino, V., Savarese, S.: Generalizing to unseen domains via adversarial data augmentation. In: NeurIPS (2018)Google Scholar
  53. 53.
    Xu, R., Li, G., Yang, J., Lin, L.: Larger norm more transferable: an adaptive feature norm approach for unsupervised domain adaptation. In: ICCV (2019)Google Scholar
  54. 54.
    Yue, X., Zhang, Y., Zhao, S., Sangiovanni-Vincentelli, A., Keutzer, K., Gong, B.: Domain randomization and pyramid consistency: simulation-to-real generalization without accessing target domain data. In: ICCV (2019)Google Scholar
  55. 55.
    Zakharov, S., Kehl, W., Ilic, S.: DeceptionNet: network-driven domain randomization. In: ICCV (2019)Google Scholar
  56. 56.
    Zheng, L., Shen, L., Tian, L., Wang, S., Wang, J., Tian, Q.: Scalable person re-identification: a benchmark. In: ICCV (2015)Google Scholar
  57. 57.
    Zheng, Z., Zheng, L., Yang, Y.: Unlabeled samples generated by GAN improve the person re-identification baseline in vitro. In: ICCV (2017)Google Scholar
  58. 58.
    Zhong, Z., Zheng, L., Li, S., Yang, Y.: Generalizing a person retrieval model hetero- and homogeneously. In: ECCV (2018)Google Scholar
  59. 59.
    Zhong, Z., Zheng, L., Zheng, Z., Li, S., Yang, Y.: Camstyle: A novel data augmentation method for person re-identification. TIP 28(3), 1176–1190 (2019)MathSciNetGoogle Scholar
  60. 60.
    Zhou, K., Xiang, T.: Torchreid: a library for deep learning person re-identification in pytorch. arXiv preprint arXiv:1910.10093 (2019)
  61. 61.
    Zhou, K., Yang, Y., Cavallaro, A., Xiang, T.: Learning generalisable omni-scale representations for person re-identification. arXiv preprint arXiv:1910.06827 (2019)
  62. 62.
    Zhou, K., Yang, Y., Cavallaro, A., Xiang, T.: Omni-scale feature learning for person re-identification. In: ICCV (2019)Google Scholar
  63. 63.
    Zhou, K., Yang, Y., Qiao, Y., Xiang, T.: Domain adaptive ensemble learning. arXiv preprint arXiv:2003.07325 (2020)
  64. 64.
    Zhu, J.Y., Park, T., Isola, P., Efros, A.A.: Unpaired image-to-image translation using cycle-consistent adversarial networks. In: ICCV (2017)Google Scholar

Copyright information

© Springer Nature Switzerland AG 2020

Authors and Affiliations

  1. 1.University of SurreyGuildfordUK
  2. 2.University of EdinburghEdinburghUK
  3. 3.Samsung AI CenterCambridgeUK

Personalised recommendations