Abstract
Unsupervised domain adaptation in semantic segmentation alleviates the reliance on expensive pixel-wise annotation. It uses a labeled source domain dataset as well as unlabeled target domain images to learn a segmentation network. In this paper, we observe two main issues of existing domain-invariant learning framework. (1) Being distracted by the feature distribution alignment, the network cannot focus on the segmentation task. (2) Fitting source domain data well would compromise the target domain performance. To address these issues, we propose DecoupleNet to alleviate source domain overfitting and let the final model focus more on the segmentation task. Also, we put forward Self-Discrimination (SD) and introduce an auxiliary classifier to learn more discriminative target domain features with pseudo labels. Finally, we propose Online Enhanced Self-Training (OEST) to contextually enhance the quality of pseudo labels in an online manner. Experiments show our method outperforms existing state-of-the-art methods. Extensive ablation studies verify the effectiveness of each component. Code is available at https://github.com/dvlab-research/DecoupleNet.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Nie, Z., Lin, Y., Yan, M., Cao, Y., Ning, S.: An adversarial training method for improving model robustness in unsupervised domain adaptation. In: Qiu, H., Zhang, C., Fei, Z., Qiu, M., Kung, S.-Y. (eds.) KSEM 2021. LNCS (LNAI), vol. 12817, pp. 3–13. Springer, Cham (2021). https://doi.org/10.1007/978-3-030-82153-1_1
Badrinarayanan, V., Kendall, A., Cipolla, R.: SegNet: a deep convolutional encoder-decoder architecture for image segmentation. Trans. Pattern Aanal. Mach. Intell. (2017)
Chen, C., et al.: Progressive feature alignment for unsupervised domain adaptation. In: CVPR (2019)
Chen, L.C., Papandreou, G., Kokkinos, I., Murphy, K., Yuille, A.: LDeepLab: semantic image segmentation with deep convolutional nets, atrous convolution, and fully connected CRFs. Trans. Pattern Anal. Mach. Intell. (2017)
Chen, L.C., Papandreou, G., Kokkinos, I., Murphy, K., Yuille, A.: LDeepLab: semantic image segmentation with deep convolutional nets, atrous convolution, and fully connected CRFs. Trans. Pattern Anal. Mach. Intell. (2018)
Chen, T., Kornblith, S., Norouzi, M., Hinton, G.E.: A simple framework for contrastive learning of visual representations. In: ICML(2020)
Chen, Y.H., Chen, W.Y., Chen, Y.T., Tsai, B.C., Frank Wang, Y.C., Sun, M.: No more discrimination: Cross city adaptation of road scene segmenters. In: ICCV (2017)
Cheng, Y., Wei, F., Bao, J., Chen, D., Wen, F., Zhang, W.: Dual path learning for domain adaptation of semantic segmentation. In: ICCV (2021)
Cicek, S., Soatto, S.: Unsupervised domain adaptation via regularized conditional alignment. In: ICCV (2019)
Cordts, M., et al.: The cityscapes dataset for semantic urban scene understanding. In: CVPR (2016)
Cui, S., Wang, S., Zhuo, J., Su, C., Huang, Q., Tian, Q.: Gradually vanishing bridge for adversarial domain adaptation. In: CVPR (2020)
Deng, Z., Luo, Y., Zhu, J.: Cluster alignment with a teacher for unsupervised domain adaptation. In: ICCV (2019)
Donahue, J., et al.: DeCAF: a deep convolutional activation feature for generic visual recognition. In: ICML (2014)
Du, L., et al.: SSF-DAN: separated semantic feature based domain adaptation network for semantic segmentation. In: ICCV (2019)
Fu, J., et al.: Dual attention network for scene segmentation. In: CVPR (2019)
Ganin, Y., Lempitsky, V.: Unsupervised domain adaptation by backpropagation. In: ICML (2015)
Gong, R., Li, W., Chen, Y., Gool, L.V.: Dlow: domain flow for adaptation and generalization. In: CVPR (2019)
Goodfellow, I.J., et al.: Generative adversarial networks. arXiv:1406.2661 (2014)
Gopalan, R., Li, R., Chellappa, R.: Domain adaptation for object recognition: an unsupervised approach. In: ICCV (2011)
Guizilini, V., Li, J., Ambrus, R., Gaidon, A.: Geometric unsupervised domain adaptation for semantic segmentation. In: ICCV (2021)
Guo, X., Yang, C., Li, B., Yuan, Y.: MetaCorrection: domain-aware meta loss correction for unsupervised domain adaptation in semantic segmentation. In: CVPR (2021)
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)
Hong, W., Wang, Z., Yang, M., Yuan, J.: Conditional generative adversarial network for structured domain adaptation. In: CVPR (2018)
Huang, J., Lu, S., Guan, D., Zhang, X.: Contextual-relation consistent domain adaptation for semantic segmentation. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12360, pp. 705–722. Springer, Cham (2020). https://doi.org/10.1007/978-3-030-58555-6_42
Huang, Z., Wang, X., Huang, L., Huang, C., Wei, Y., Liu, W.: CCNet: crisis-cross attention for semantic segmentation. In: ICCV (2019)
Kang, G., Wei, Y., Yang, Y., Zhuang, Y., Hauptmann, A.: Pixel-level cycle association: A new perspective for domain adaptive semantic segmentation. In: NeurIPS (2020)
Kang, G., Zheng, L., Yan, Y., Yang, Y.: Deep adversarial attention alignment for unsupervised domain adaptation: the benefit of target expectation maximization. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) ECCV 2018. LNCS, vol. 11215, pp. 420–436. Springer, Cham (2018). https://doi.org/10.1007/978-3-030-01252-6_25
Kim, M., Byun, H.: Learning texture invariant representation for domain adaptation of semantic segmentation. In: CVPR (2020)
Kurmi, V.K., Kumar, S., Namboodiri, V.P.: Attending to discriminative certainty for domain adaptation. In: CVPR (2019)
Lai, X., et al.: Semi-supervised semantic segmentation with directional context-aware consistency. In: CVPR (2021)
Lee, S., Kim, D., Kim, N., Jeong, S.G.: Drop to adapt: Learning discriminative features for unsupervised domain adaptation. In: ICCV (2019)
Li, S., et al.: Semantic concentration for domain adaptation. In: ICCV (2021)
Li, Y., Wang, N., Shi, J., Liu, J., Hou, X.: Revisiting batch normalization for practical domain adaptation. arXiv:1603.04779 (2016)
Li, Y., Yuan, L., Vasconcelos, N.: Bidirectional learning for domain adaptation of semantic segmentation. In: CVPR (2019)
Liu, H., Long, M., Wang, J., Jordan, M.: Transferable adversarial training: a general approach to adapting deep classifiers. In: ICML (2019)
Liu, M.Y., Tuzel, O.: Coupled generative adversarial networks. arXiv:1606.07536 (2016)
Liu, W., Rabinovich, A., Berg, A.C.: ParseNet: looking wider to see better. arXiv (2015)
Liu, W., Ferstl, D., Schulter, S., Zebedin, L., Fua, P., Leistner, C.: Domain adaptation for semantic segmentation via patch-wise contrastive learning. arXiv:2104.11056 (2021)
Liu, X., et al.: Adversarial unsupervised domain adaptation with conditional and label shift: Infer, align and iterate. In: ICCV (2021)
Liu, X., Li, S., Ge, Y., Ye, P., You, J., Lu, J.: Recursively conditional gaussian for ordinal unsupervised domain adaptation. In: ICCV (2021)
Long, M., Cao, Y., Wang, J., Jordan, M.: Learning transferable features with deep adaptation networks. In: ICML (2015)
Long, M., Zhu, H., Wang, J., Jordan, M.I.: Unsupervised domain adaptation with residual transfer networks. arXiv:1602.04433 (2016)
Long, M., Zhu, H., Wang, J., Jordan, M.I.: Deep transfer learning with joint adaptation networks. In: ICML (2017)
Luo, Y., Liu, P., Guan, T., Yu, J., Yang, Y.: Significance-aware information bottleneck for domain adaptive semantic segmentation. In: ICCV (2019)
Luo, Y., Zheng, L., Guan, T., Yu, J., Yang, Y.: Taking a closer look at domain shift: Category-level adversaries for semantics consistent domain adaptation. In: CVPR (2019)
Ma, X., Zhang, T., Xu, C.: GCAN: graph convolutional adversarial network for unsupervised domain adaptation. In: CVPR (2019)
Mancini, M., Porzi, L., Bulo, S.R., Caputo, B., Ricci, E.: Boosting domain adaptation by discovering latent domains. In: CVPR (2018)
Mao, X., Li, Q., Xie, H., Lau, R.Y.K., Wang, Z., Smolley, S.P.: Least squares generative adversarial networks. In: ICCV (2017)
Maria Carlucci, F., Porzi, L., Caputo, B., Ricci, E., Rota Bulo, S.: Autodial: Automatic domain alignment layers. In: ICCV (2017)
Mei, K., Zhu, C., Zou, J., Zhang, S.: Instance adaptive self-training for unsupervised domain adaptation. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12371, pp. 415–430. Springer, Cham (2020). https://doi.org/10.1007/978-3-030-58574-7_25
Noh, H., Hong, S., Han, B.: Learning deconvolution network for semantic segmentation. In: ICCV (2015)
Pandey, P., Tyagi, A.K., Ambekar, S., Prathosh, A.P.: Unsupervised domain adaptation for semantic segmentation of NIR images through generative latent search. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12351, pp. 413–429. Springer, Cham (2020). https://doi.org/10.1007/978-3-030-58539-6_25
Peng, X., Li, Y., Saenko, K.: Domain2Vec: domain embedding for unsupervised domain adaptation. arXiv:2007.09257 (2020)
Richter, S.R., Vineet, V., Roth, S., Koltun, V.: Playing for data: ground truth from computer games. In: ECCV (2016)
Ronneberger, O., Fischer, P., Brox, T.: U-Net: convolutional networks for biomedical image segmentation. In: Navab, N., Hornegger, J., Wells, W.M., Frangi, A.F. (eds.) MICCAI 2015. LNCS, vol. 9351, pp. 234–241. Springer, Cham (2015). https://doi.org/10.1007/978-3-319-24574-4_28
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 (2016)
Shelhamer, E., Long, J., Darrell, T.: Fully convolutional networks for semantic segmentation. Trans. Pattern Anal. Mach. Intell. (2017)
Shin, I., Woo, S., Pan, F., Kweon, I.S.: Two-phase pseudo label densification for self-training based domain adaptation. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12358, pp. 532–548. Springer, Cham (2020). https://doi.org/10.1007/978-3-030-58601-0_32
Sohn, K., Fixmatch: Simplifying semi-supervised learning with consistency and confidence. In: NeurIPS (2020)
Sun, B., Saenko, K.: Deep CORAL: correlation alignment for deep domain adaptation. In: Hua, G., Jégou, H. (eds.) ECCV 2016. LNCS, vol. 9915, pp. 443–450. Springer, Cham (2016). https://doi.org/10.1007/978-3-319-49409-8_35
Torralba, A., Efros, A.A.: Unbiased look at dataset bias. In: CVPR (2011)
Truong, T.D., Duong, C.N., Le, N., Phung, S.L., Rainwater, C., Luu, K.: BiMaL: Bijective maximum likelihood approach to domain adaptation in semantic scene segmentation. In: ICCV (2021)
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 (2018)
Tsai, Y.H., Sohn, K., Schulter, S., Chandraker, M.: Domain adaptation for structured output via discriminative patch representations. In: ICCV (2019)
Tzeng, E., Hoffman, J., Saenko, K., Darrell, T.: Adversarial discriminative domain adaptation. In: CVPR (2017)
Tzeng, E., Hoffman, J., Zhang, N., Saenko, K., Darrell, T.: Deep domain confusion: Maximizing for domain invariance. arXiv:1412.3474 (2014)
Volpi, R., Morerio, P., Savarese, S., Murino, V.: Adversarial feature augmentation for unsupervised domain adaptation. In: CVPR (2018)
Vu, T.H., Jain, H., Bucher, M., Cord, M., Pérez, P.: Advent: adversarial entropy minimization for domain adaptation in semantic segmentation. In: CVPR (2019)
Wang, H., Shen, T., Zhang, W., Duan, L.-Y., Mei, T.: Classes matter: a fine-grained adversarial approach to cross-domain semantic segmentation. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12359, pp. 642–659. Springer, Cham (2020). https://doi.org/10.1007/978-3-030-58568-6_38
Wang, Q., Dai, D., Hoyer, L., Van Gool, L., Fink, O.: Domain adaptive semantic segmentation with self-supervised depth estimation. In: ICCV (2021)
Wei, G., Lan, C., Zeng, W., Chen, Z.: MetaAlign: coordinating domain alignment and classification for unsupervised domain adaptation. In: CVPR (2021)
Woong-Gi, C., Tackgeun, Y., Seonguk, S., Suha, K., Bohyung, H.: Domain-specific batch normalization for unsupervised domain adaptation. In: CVPR (2019)
Xie, S., Zheng, Z., Chen, L., Chen, C.: Learning semantic representations for unsupervised domain adaptation. In: ICML (2018)
Xu, M., Zhang, J., Ni, B., Li, T., Wang, C., Tian, Q., Zhang, W.: Adversarial domain adaptation with domain mixup. In: AAAI (2020)
Yang, J., et al.: An adversarial perturbation oriented domain adaptation approach for semantic segmentation. In: AAAI (2020)
Yang, J., An, W., Wang, S., Zhu, X., Yan, C., Huang, J.: Label-driven reconstruction for domain adaptation in semantic segmentation. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12372, pp. 480–498. Springer, Cham (2020). https://doi.org/10.1007/978-3-030-58583-9_29
Yang, J., et al.: Exploring robustness of unsupervised domain adaptation in semantic segmentation. In: ICCV (2021)
Yang, M., Yu, K., Zhang, C., Li, Z., Yang, K.: DenseASPP for semantic segmentation in street scenes. In: CVPR (2018)
Yang, Y., Soatto, S.: FDA: Fourier domain adaptation for semantic segmentation. In: CVPR (2020)
Yu, F., Koltun, V.: Multi-scale context aggregation by dilated convolutions. In: ICLR (2016)
Zhang, F., Koltun, V., Torr, P., Ranftl, R., Richter, S.R.: Unsupervised contrastive domain adaptation for semantic segmentation. arXiv:2204.08399 (2022)
Zhang, P., Zhang, B., Zhang, T., Chen, D., Wang, Y., Wen, F.: Prototypical pseudo label denoising and target structure learning for domain adaptive semantic segmentation. In: CVPR (2021)
Zhang, Q., Zhang, J., Liu, W., Tao, D.: Category anchor-guided unsupervised domain adaptation for semantic segmentation. In: NeurIPS (2019)
Zhang, Y., Tang, H., Jia, K., Tan, M.: Domain-symmetric networks for adversarial domain adaptation. In: CVPR (2019)
Zhao, H., Qi, X., Shen, X., Shi, J., Jia, J.: ICNet for real-time semantic segmentation on high-resolution images. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) ECCV 2018. LNCS, vol. 11207, pp. 418–434. Springer, Cham (2018). https://doi.org/10.1007/978-3-030-01219-9_25
Zhao, H., Shi, J., Qi, X., Wang, X., Jia, J.: Pyramid scene parsing network. In: CVPR (2017)
Zhao, H., Zhang, Y., Liu, S., Shi, J., Loy, C.C., Lin, D., Jia, J.: PSANet: point-wise spatial attention network for scene parsing. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) ECCV 2018. LNCS, vol. 11213, pp. 270–286. Springer, Cham (2018). https://doi.org/10.1007/978-3-030-01240-3_17
Zhu, Z., Xu, M., Bai, S., Huang, T., Bai, X.: Asymmetric non-local neural networks for semantic segmentation. In: ICCV (2019)
Zou, Y., Yu, Z., Vijaya Kumar, B.V.K., Wang, J.: Unsupervised domain adaptation for semantic segmentation via class-balanced self-training. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) ECCV 2018. LNCS, vol. 11207, pp. 297–313. Springer, Cham (2018). https://doi.org/10.1007/978-3-030-01219-9_18
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
© 2022 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Lai, X. et al. (2022). DecoupleNet: Decoupled Network for Domain Adaptive Semantic Segmentation. In: Avidan, S., Brostow, G., Cissé, M., Farinella, G.M., Hassner, T. (eds) Computer Vision – ECCV 2022. ECCV 2022. Lecture Notes in Computer Science, vol 13693. Springer, Cham. https://doi.org/10.1007/978-3-031-19827-4_22
Download citation
DOI: https://doi.org/10.1007/978-3-031-19827-4_22
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-19826-7
Online ISBN: 978-3-031-19827-4
eBook Packages: Computer ScienceComputer Science (R0)