Abstract
We propose a simple but effective multi-source domain generalization technique based on deep neural networks by incorporating optimized normalization layers that are specific to individual domains. Our approach employs multiple normalization methods while learning separate affine parameters per domain. For each domain, the activations are normalized by a weighted average of multiple normalization statistics. The normalization statistics are kept track of separately for each normalization type if necessary. Specifically, we employ batch and instance normalizations in our implementation to identify the best combination of these two normalization methods in each domain. The optimized normalization layers are effective to enhance the generalizability of the learned model. We demonstrate the state-of-the-art accuracy of our algorithm in the standard domain generalization benchmarks, as well as viability to further tasks such as multi-source domain adaptation and domain generalization in the presence of label noise.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Ba, L.J., Kiros, R., Hinton, G.E.: Layer normalization. arXiv preprint arXiv:1607.06450 (2016)
Balaji, Y., Sankaranarayanan, S., Chellappa, R.: MetaReg: towards domain generalization using meta-regularization. In: NeurIPS (2018)
Bilen, H., Vedaldi, A.: Universal representations: the missing link between faces, text, planktons, and cat breeds. arXiv preprint arXiv:1701.07275 (2017)
Carlucci, F.M., D’Innocente, A., Bucci, S., Caputo, B., Tommasi, T.: Domain generalization by solving jigsaw puzzles. In: CVPR (2019)
Chang, W.G., You, T., Seo, S., Kwak, S., Han, B.: Domain specific batch normalization for unsupervised domain adaptation. In: CVPR (2019)
D’Innocente, A., Caputo, B.: Domain generalization with domain-specific aggregation modules. In: Brox, T., Bruhn, A., Fritz, M. (eds.) GCPR 2018. LNCS, vol. 11269, pp. 187–198. Springer, Cham (2019). https://doi.org/10.1007/978-3-030-12939-2_14
Dou, Q., de Castro, D.C., Kamnitsas, K., Glocker, B.: Domain generalization via model-agnostic learning of semantic features. In: NeruIPS (2019)
Finn, C., Abbeel, P., Levine, S.: Model-agnostic meta-learning for fast adaptation of deep networks. In: ICML (2017)
Guo, J., Shah, D., Barzilay, R.: Multi-source domain adaptation with mixture of experts. In: EMNLP (2018)
Huang, X., Belongie, S.: Arbitrary style transfer in real-time with adaptive instance normalization. In: ICCV (2017)
Ioffe, S., Szegedy, C.: Batch normalization: accelerating deep network training by reducing internal covariate shift. In: ICML (2015)
Li, D., Yang, Y., Song, Y.Z., Hospedales, T.: Learning to generalize: meta-learning for domain generalization. In: AAAI (2018)
Li, D., Yang, Y., Song, Y.Z., Hospedales, T.M.: Deeper, broader and artier domain generalization. In: ICCV (2017)
Li, D., Zhang, J., Yang, Y., Liu, C., Song, Y.Z., Hospedales, T.M.: Episodic training for domain generalization (2019)
Li, Y., Gong, M., Tian, X., Liu, T., Tao, D.: Domain generalization via conditional invariant representations. In: AAAI (2018)
Luo, P., Ren, J., Peng, Z.: Differentiable learning-to-normalize via switchable normalization. In: ICLR (2019)
Mancini, M., Bulò, S.R., Caputo, B., Ricci, E.: Best sources forward: domain generalization through source-specific nets. In: ICIP (2018)
Matsuura, T., Harada, T.: Domain generalization using a mixture of multiple latent domains. In: AAAI (2020)
Miyato, T., Kataoka, T., Koyama, M., Yoshida, Y.: Spectral normalization for generative adversarial networks. In: ICLR (2018)
Motiian, S., Piccirilli, M., Adjeroh, D.A., Doretto, G.: Unified deep supervised domain adaptation and generalization. In: ICCV (2017)
Muandet, K., Balduzzi, D., Schölkopf, B.: Domain generalization via invariant feature representation. In: ICML (2013)
Nam, H., Kim, H.E.: Batch-instance normalization for adaptively style-invariant neural networks. In: NeurIPS (2018)
Pan, X., Luo, P., Shi, J., Tang, X.: Two at once: enhancing learning and generalization capacities via IBN-Net. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) ECCV 2018. LNCS, vol. 11208, pp. 484–500. Springer, Cham (2018). https://doi.org/10.1007/978-3-030-01225-0_29
Salimans, T., Kingma, D.P.: Weight normalization: a simple reparameterization to accelerate training of deep neural networks. In: NIPS (2016)
Shao, W., et al.: SSN: learning sparse switchable normalization via sparsestmax. In: CVPR (2019)
Shu, Y., Cao, Z., Long, M., Wang, J.: Transferable curriculum for weakly-supervised domain adaptation. In: AAAI (2018)
Ulyanov, D., Vedaldi, A., Lempitsky, V.: Improved Texture Networks: Maximizing Quality and Diversity in Feed-Forward Stylization and Texture Synthesis. In: CVPR (2017)
Venkateswara, H., Eusebio, J., Chakraborty, S., Panchanathan, S.: Deep hashing network for unsupervised domain adaptation. In: CVPR (2017)
Wu, Y., He, K.: Group normalization. Int. J. Comput. Vis. 128(3), 742–755 (2019). https://doi.org/10.1007/s11263-019-01198-w
Xu, R., Chen, Z., Zuo, W., Yan, J., Lin, L.: Deep cocktail network: multi-source unsupervised domain adaptation with category shift. In: CVPR (2018)
Zhao, H., Zhang, S., Wu, G., Moura, J.M.F., Costeira, J.P., Gordon, G.J.: Adversarial multiple source domain adaptation. In: NeurIPS (2018)
Acknowledgement
This work was supported by Institute for Information & Communications Technology Promotion (IITP) grant funded by the Korea government (MSIT) [2016-0-00563, 2017-0-01779].
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
Seo, S., Suh, Y., Kim, D., Kim, G., Han, J., Han, B. (2020). Learning to Optimize Domain Specific Normalization 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 12367. Springer, Cham. https://doi.org/10.1007/978-3-030-58542-6_5
Download citation
DOI: https://doi.org/10.1007/978-3-030-58542-6_5
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-58541-9
Online ISBN: 978-3-030-58542-6
eBook Packages: Computer ScienceComputer Science (R0)