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.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Notes
- 1.
Following [31], homogeneous DG shares the same label space between training and test data while heterogeneous DG has disjoint label space.
- 2.
The searching space is: \(\lambda _{\mathrm {Domain}} \in \{0.5, 1, 2\}\), \(\lambda _{\mathrm {Cycle}} \in \{10, 20\}\) and \(\lambda _{\mathrm {CE}} \in \{1\}\).
References
Arjovsky, M., Chintala, S., Bottou, L.: Wasserstein generative adversarial networks. In: ICML (2017)
Balaji, Y., Sankaranarayanan, S., Chellappa, R.: MetaReg: towards domain generalization using meta-regularization. In: NeurIPS (2018)
Bellemare, M.G., et al.: The cramer distance as a solution to biased wasserstein gradients. arXiv preprint arXiv:1705.10743 (2017)
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/s10994-009-5152-4
Carlucci, F.M., D’Innocente, A., Bucci, S., Caputo, B., Tommasi, T.: Domain generalization by solving jigsaw puzzles. In: CVPR (2019)
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)
Cuturi, M.: Sinkhorn distances: lightspeed computation of optimal transport. In: NeurIPS (2013)
Deng, J., Dong, W., Socher, R., Li, L.J., Li, K., Fei-Fei, L.: ImageNet: a large-scale hierarchical image database. In: CVPR (2009)
D’Innocente, A., Caputo, B.: Domain generalization with domain-specific aggregation modules. In: GCPR (2018)
Dou, Q., Castro, D.C., Kamnitsas, K., Glocker, B.: Domain generalization via model-agnostic learning of semantic features. In: NeurIPS (2019)
Gan, C., Yang, T., Gong, B.: Learning attributes equals multi-source domain generalization. In: CVPR (2016)
Ganin, Y., Lempitsky, V.S.: Unsupervised domain adaptation by backpropagation. In: ICML (2015)
Ganin, Y., et al.: Domain-adversarial training of neural networks. JMLR 17(1), 2030–2096 (2016)
Genevay, A., Peyré, G., Cuturi, M.: Learning generative models with sinkhorn divergences. In: AISTATS (2018)
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)
Ghifary, M., Kleijn, W.B., Zhang, M., Balduzzi, D.: Domain generalization for object recognition with multi-task autoencoders. In: ICCV (2015)
Goodfellow, I., et al.: Generative adversarial nets. In: NeurIPS (2014)
Goodfellow, I.J., Shlens, J., Szegedy, C.: Explaining and harnessing adversarial examples. In: ICLR (2015)
He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: CVPR (2016)
Hoffman, J., et al.: CyCADA: cycle-consistent adversarial domain adaptation. In: ICML (2018)
Hospedales, T., Antoniou, A., Micaelli, P., Storkey, A.: Meta-learning in neural networks: a survey. arXiv preprint arXiv:2004.05439 (2020)
Jin, X., Lan, C., Zeng, W., Chen, Z., Zhang, L.: Style normalization and restitution for generalizable person re-identification. In: CVPR (2020)
Kingma, D.P., Ba, J.: Adam: a method for stochastic optimization. In: ICLR (2014)
LeCun, Y., Bottou, L., Bengio, Y., Haffner, P.: Gradient-based learning applied to document recognition. Proc. IEEE 86(11), 2278–2324 (1998)
Li, D., Yang, Y., Song, Y.Z., Hospedales, T.M.: Deeper, broader and artier domain generalization. In: ICCV (2017)
Li, D., Yang, Y., Song, Y.Z., Hospedales, T.M.: Learning to generalize: meta-learning for domain generalization. In: AAAI (2018)
Li, D., Zhang, J., Yang, Y., Liu, C., Song, Y.Z., Hospedales, T.M.: Episodic training for domain generalization. In: ICCV (2019)
Li, H., Jialin Pan, S., Wang, S., Kot, A.C.: Domain generalization with adversarial feature learning. In: CVPR (2018)
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)
Li, Y., Fang, C., Yang, J., Wang, Z., Lu, X., Yang, M.H.: Diversified texture synthesis with feed-forward networks. In: CVPR (2017)
Li, Y., Yang, Y., Zhou, W., Hospedales, T.: Feature-critic networks for heterogeneous domain generalization. In: ICML (2019)
Liu, J., Zha, Z.J., Chen, D., Hong, R., Wang, M.: Adaptive transfer network for cross-domain person re-identification. In: CVPR (2019)
Long, M., Cao, Y., Wang, J., Jordan, M.I.: Learning transferable features with deep adaptation networks. In: ICML (2015)
Maaten, L.V.D., Hinton, G.: Visualizing data using t-SNE. JMLR 9, 2579–2605 (2008)
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)
Motiian, S., Piccirilli, M., Adjeroh, D.A., Doretto, G.: Unified deep supervised domain adaptation and generalization. In: ICCV (2017)
Muandet, K., Balduzzi, D., Scholkopf, B.: Domain generalization via invariant feature representation. In: ICML (2013)
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)
Noroozi, M., Favaro, P.: Unsupervised learning of visual representations by solving jigsaw puzzles. In: ECCV (2016)
Peng, X., Bai, Q., Xia, X., Huang, Z., Saenko, K., Wang, B.: Moment matching for multi-source domain adaptation. In: ICCV (2019)
Peyré, G., Cuturi, M., et al.: Computational optimal transport. Found. Trends Mach. Learn. 11(5–6), 355–607 (2019)
Prakash, A., et al.: Structured domain randomization: bridging the reality gap by context-aware synthetic data. In: ICRA (2019)
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)
Saito, K., Kim, D., Sclaroff, S., Darrell, T., Saenko, K.: Semi-supervised domain adaptation via minimax entropy. In: ICCV (2019)
Salimans, T., Zhang, H., Radford, A., Metaxas, D.: Improving GANs using optimal transport. In: ICLR (2018)
Shaham, T.R., Dekel, T., Michaeli, T.: Singan: Learning a generative model from a single natural image. In: ICCV (2019)
Shankar, S., Piratla, V., Chakrabarti, S., Chaudhuri, S., Jyothi, P., Sarawagi, S.: Generalizing across domains via cross-gradient training. In: ICLR (2018)
Szegedy, C., et al.: Intriguing properties of neural networks. In: ICLR (2014)
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)
Tzeng, E., Hoffman, J., Saenko, K., Darrell, T.: Adversarial discriminative domain adaptation. In: CVPR (2017)
Venkateswara, H., Eusebio, J., Chakraborty, S., Panchanathan, S.: Deep hashing network for unsupervised domain adaptation. In: CVPR (2017)
Volpi, R., Namkoong, H., Sener, O., Duchi, J., Murino, V., Savarese, S.: Generalizing to unseen domains via adversarial data augmentation. In: NeurIPS (2018)
Xu, R., Li, G., Yang, J., Lin, L.: Larger norm more transferable: an adaptive feature norm approach for unsupervised domain adaptation. In: ICCV (2019)
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)
Zakharov, S., Kehl, W., Ilic, S.: DeceptionNet: network-driven domain randomization. In: ICCV (2019)
Zheng, L., Shen, L., Tian, L., Wang, S., Wang, J., Tian, Q.: Scalable person re-identification: a benchmark. In: ICCV (2015)
Zheng, Z., Zheng, L., Yang, Y.: Unlabeled samples generated by GAN improve the person re-identification baseline in vitro. In: ICCV (2017)
Zhong, Z., Zheng, L., Li, S., Yang, Y.: Generalizing a person retrieval model hetero- and homogeneously. In: ECCV (2018)
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)
Zhou, K., Xiang, T.: Torchreid: a library for deep learning person re-identification in pytorch. arXiv preprint arXiv:1910.10093 (2019)
Zhou, K., Yang, Y., Cavallaro, A., Xiang, T.: Learning generalisable omni-scale representations for person re-identification. arXiv preprint arXiv:1910.06827 (2019)
Zhou, K., Yang, Y., Cavallaro, A., Xiang, T.: Omni-scale feature learning for person re-identification. In: ICCV (2019)
Zhou, K., Yang, Y., Qiao, Y., Xiang, T.: Domain adaptive ensemble learning. arXiv preprint arXiv:2003.07325 (2020)
Zhu, J.Y., Park, T., Isola, P., Efros, A.A.: Unpaired image-to-image translation using cycle-consistent adversarial networks. In: ICCV (2017)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
1 Electronic supplementary material
Below is the link to the electronic supplementary material.
Rights and permissions
Copyright information
© 2020 Springer Nature Switzerland AG
About this paper
Cite this paper
Zhou, K., Yang, Y., Hospedales, T., Xiang, T. (2020). Learning to Generate Novel Domains for Domain Generalization. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, JM. (eds) Computer Vision – ECCV 2020. ECCV 2020. Lecture Notes in Computer Science(), vol 12361. Springer, Cham. https://doi.org/10.1007/978-3-030-58517-4_33
Download citation
DOI: https://doi.org/10.1007/978-3-030-58517-4_33
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-58516-7
Online ISBN: 978-3-030-58517-4
eBook Packages: Computer ScienceComputer Science (R0)