Abstract
The divergence between labeled training data and unlabeled testing data is a significant challenge for recent deep learning models. Unsupervised domain adaptation (UDA) attempts to solve such a problem. Recent works show that self-training is a powerful approach to UDA. However, existing methods have difficulty in balancing scalability and performance. In this paper, we propose an instance adaptive self-training framework for UDA on the task of semantic segmentation. To effectively improve the quality of pseudo-labels, we develop a novel pseudo-label generation strategy with an instance adaptive selector. Besides, we propose the region-guided regularization to smooth the pseudo-label region and sharpen the non-pseudo-label region. Our method is so concise and efficient that it is easy to be generalized to other unsupervised domain adaptation methods. Experiments on ‘GTA5 to Cityscapes’ and ‘SYNTHIA to Cityscapes’ demonstrate the superior performance of our approach compared with the state-of-the-art methods.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Baktashmotlagh, M., Harandi, M.T., Lovell, B.C., Salzmann, M.: Unsupervised domain adaptation by domain invariant projection. In: ICCV, pp. 769–776 (2013)
Chen, C., et al.: Progressive feature alignment for unsupervised domain adaptation. In: CVPR, pp. 627–636 (2019)
Chen, L.C., Papandreou, G., Kokkinos, I., Murphy, K., Yuille, A.L.: DeepLab: semantic image segmentation with deep convolutional nets, atrous convolution, and fully connected CRFs. TPAMI 40(4), 834–848 (2017)
Chen, Y., Li, W., Sakaridis, C., Dai, D., Van Gool, L.: Domain adaptive faster R-CNN for object detection in the wild. In: CVPR, pp. 3339–3348 (2018)
Cordts, M., et al.: The cityscapes dataset for semantic urban scene understanding. In: CVPR, pp. 3213–3223 (2016)
Du, L., et al.: SSF-DAN: separated semantic feature based domain adaptation network for semantic segmentation. In: ICCV (2019)
Goodfellow, I., Bengio, Y., Courville, A.: Deep Learning. MIT Press, Cambridge (2016)
He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: CVPR, pp. 770–778 (2016)
Hoffman, J., et al.: Cycada: cycle-consistent adversarial domain adaptation. In: ICML (2018)
Huang, X., Liu, M.Y., Belongie, S., Kautz, J.: Multimodal unsupervised image-to-image translation. In: ECCV, pp. 172–189 (2018)
Hung, W.C., Tsai, Y.H., Liou, Y.T., Lin, Y.Y., Yang, M.H.: Adversarial learning for semi-supervised semantic segmentation. In: BMVC (2019)
Kalluri, T., Varma, G., Chandraker, M., Jawahar, C.: Universal semi-supervised semantic segmentation. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 5259–5270 (2019)
Kan, M., Shan, S., Chen, X.: Bi-shifting auto-encoder for unsupervised domain adaptation. In: ICCV, pp. 3846–3854 (2015)
Krizhevsky, A., Sutskever, I., Hinton, G.E.: Imagenet classification with deep convolutional neural networks. In: NIPS, pp. 1097–1105 (2012)
Kukačka, J., Golkov, V., Cremers, D.: Regularization for deep learning: a taxonomy. arXiv preprint arXiv:1710.10686 (2017)
Lee, C.Y., Batra, T., Baig, M.H., Ulbricht, D.: Sliced wasserstein discrepancy for unsupervised domain adaptation. In: CVPR, pp. 10285–10295 (2019)
Li, J., et al.: Multi-human parsing machines. In: ACM Multimedia, pp. 45–53 (2018)
Li, M., Zhou, Z.-H.: SETRED: self-training with editing. In: Ho, T.B., Cheung, D., Liu, H. (eds.) PAKDD 2005. LNCS (LNAI), vol. 3518, pp. 611–621. Springer, Heidelberg (2005). https://doi.org/10.1007/11430919_71
Li, Y., Yuan, L., Vasconcelos, N.: Bidirectional learning for domain adaptation of semantic segmentation. In: CVPR (2019)
Lian, Q., Lv, F., Duan, L., Gong, B.: Constructing self-motivated pyramid curriculums for cross-domain semantic segmentation: a non-adversarial approach. In: CVPR, pp. 6758–6767 (2019)
Long, M., Cao, Z., Wang, J., Jordan, M.I.: Conditional adversarial domain adaptation. In: NIPS, pp. 1640–1650 (2018)
Luo, Y., Liu, P., Guan, T., Yu, J., Yang, Y.: Significance-aware information bottleneck for domain adaptive semantic segmentation. In: ICCV (2019)
Richter, S.R., Vineet, V., Roth, S., Koltun, V.: Playing for data: ground truth from computer games. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016. LNCS, vol. 9906, pp. 102–118. Springer, Cham (2016). https://doi.org/10.1007/978-3-319-46475-6_7
Ros, G., Sellart, L., Materzynska, J., Vazquez, D., Lopez, A.M.: The synthia dataset: a large collection of synthetic images for semantic segmentation of urban scenes. In: CVPR, pp. 3234–3243 (2016)
Szegedy, C., Vanhoucke, V., Ioffe, S., Shlens, J., Wojna, Z.: Rethinking the inception architecture for computer vision. In: CVPR, pp. 2818–2826 (2016)
Triguero, I., García, S., Herrera, F.: Self-labeled techniques for semi-supervised learning: taxonomy, software and empirical study. KAIS 42(2), 245–284 (2015)
Tsai, Y.H., Hung, W.C., Schulter, S., Sohn, K., Yang, M.H., Chandraker, M.: Learning to adapt structured output space for semantic segmentation. In: CVPR, pp. 7472–7481 (2018)
Tsai, Y.H., Sohn, K., Schulter, S., Chandraker, M.: Domain adaptation for structured output via discriminative patch representations. In: CVPR (2019)
Vu, T.H., Jain, H., Bucher, M., Cord, M., Pérez, P.: Advent: adversarial entropy minimization for domain adaptation in semantic segmentation. In: CVPR (2019)
Yang, J., Xu, R., Li, R., Qi, X., Shen, X., Li, G., Lin, L.: An adversarial perturbation oriented domain adaptation approach for semantic segmentation. In: AAAI (2020)
Zhang, Q., Zhang, J., Liu, W., Tao, D.: Category anchor-guided unsupervised domain adaptation for semantic segmentation. In: NeurIPS, pp. 433–443 (2019)
Zhao, J., et al.: Towards pose invariant face recognition in the wild. In: CVPR, pp. 2207–2216 (2018)
Zhao, J., et al.: Self-supervised neural aggregation networks for human parsing. In: CVPRW, pp. 7–15 (2017)
Zheng, Z., Yang, Y.: Unsupervised scene adaptation with memory regularization in vivo. arXiv preprint arXiv:1912.11164 (2019)
Zou, Y., Yu, Z., Liu, X., Kumar, B., Wang, J.: Confidence regularized self-training. In: ICCV, pp. 5982–5991 (2019)
Zou, Y., Yu, Z., Vijaya Kumar, B., Wang, J.: Unsupervised domain adaptation for semantic segmentation via class-balanced self-training. In: ECCV, pp. 289–305 (2018)
Acknowledgement
This work was supported in part by the Natural Science Foundation of Beijing Municipality under Grant 4182044.
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
Mei, K., Zhu, C., Zou, J., Zhang, S. (2020). Instance Adaptive Self-training for Unsupervised Domain Adaptation. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, JM. (eds) Computer Vision – ECCV 2020. ECCV 2020. Lecture Notes in Computer Science(), vol 12371. Springer, Cham. https://doi.org/10.1007/978-3-030-58574-7_25
Download citation
DOI: https://doi.org/10.1007/978-3-030-58574-7_25
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-58573-0
Online ISBN: 978-3-030-58574-7
eBook Packages: Computer ScienceComputer Science (R0)