Abstract
To alleviate the domain gap, we propose an improved domain adaptative network for semantic segmentation. Specifically, we use the method of distinguishing alignment between foreground and background classes for fine-grained adaptating diffrent type of categories. Furthermore, we use a channel and spatial paraller attention module to acquire the rich spatial and channel information from features. However, it will still causes a large inter-domain difference due to the different feature distributions between different domains. We use the self-supervised learning method to generate pseudo labels for better aligning target domain. Finally, we use focal loss in the target domain to alleviate the impact of categories imbalance on the adaptation process. Experiments show that our method achieves better segmentation performance in unsupervised domain adaptative semantic segmentation.
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
Chen, M., Xue, H., Cai, D.: Domain adaptation for semantic segmentation with maximum squares loss. In: ICCV, pp. 2090–2099 (2019)
Chen, Y., Li, W., Van Gool, L.: Road: reality oriented adaptation for semantic segmentation of urban scenes. In: CVPR, pp. 7892–7901 (2018)
Cordts, M., et al.: The cityscapes dataset for semantic urban scene understanding. In: CVPR, pp. 3213–3223 (2016)
Hoffman, J., Wang, D., Yu, F., Darrell, T.: FCNs in the wild: pixel-level adversarial and constraint-based adaptation. arXiv preprint arXiv:1612.02649 (2016)
Hu, J., Shen, L., Sun, G.: Squeeze-and-excitation networks. In: CVPR, pp. 7132–7141 (2018)
Huang, J., Lu, S., Guan, D., Zhang, X.: Contextual-relation consistent domain adaptation for semantic segmentation. In: ECCV, pp. 705–722 (2020)
Kang, G., Wei, Y., Yang, Y., Zhuang, Y., Hauptmann, A.G.: Pixel-level cycle association: a new perspective for domain adaptive semantic segmentation. arXiv preprint arXiv:2011.00147 (2020)
Laine, S., Aila, T.: Temporal ensembling for semi-supervised learning. arXiv preprint arXiv:1610.02242 (2016)
Li, Y., Yuan, L., Vasconcelos, N.: Bidirectional learning for domain adaptation of semantic segmentation. In: CVPR, pp. 6936–6945 (2019)
Lin, T.Y., Goyal, P., Girshick, R., He, K., Dollár, P.: Focal loss for dense object detection. In: ICCV, pp. 2980–2988 (2017)
Luo, Y., Liu, P., Guan, T., Yu, J., Yang, Y.: Significance-aware information bottleneck for domain adaptive semantic segmentation. In: ICCV, pp. 6778–6787 (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, pp. 2507–2516 (2019)
Richter, S.R., Vineet, V., Roth, S., Koltun, V.: Playing for data: ground truth from computer games. In: ECCV, pp. 102–118 (2016)
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)
Roy, A.G., Navab, N., Wachinger, C.: Concurrent spatial and channel ‘squeeze & excitation ’in fully convolutional networks. In: ICMICCAI, pp. 421–429 (2018)
Subhani, M.N., Ali, M.: Learning from scale-invariant examples for domain adaptation in semantic segmentation. arXiv preprint arXiv:2007.14449 (2020)
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: ICCV, pp. 1456–1465 (2019)
Tzeng, E., Hoffman, J., Saenko, K., Darrell, T.: Adversarial discriminative domain adaptation. In: CVPR, pp. 7167–7176 (2017)
Wang, H., Shen, T., Zhang, W., Duan, L.Y., Mei, T.: Classes matter: a fine-grained adversarial approach to cross-domain semantic segmentation. In: ECCV, pp. 642–659 (2020)
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: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 34, pp. 12613–12620 (2020)
Zhang, H., Goodfellow, I., Metaxas, D., Odena, A.: Self-attention generative adversarial networks. In: ICML, pp. 7354–7363 (2019)
Zhang, J., Li, Z., Zhang, C., Ma, H.: Stable self-attention adversarial learning for semi-supervised semantic image segmentation. J. Vis. Commun. Image Represent. 78, 103170 (2021)
Zheng, Z., Yang, Y.: Rectifying pseudo label learning via uncertainty estimation for domain adaptive semantic segmentation. Int. J. Comput. Vis. 129, 1106–1120 (2021)
Zou, Y., Yu, Z., Kumar, B., Wang, J.: Unsupervised domain adaptation for semantic segmentation via class-balanced self-training. In: ECCV, pp. 289–305 (2018)
Zou, Y., Yu, Z., Liu, X., Kumar, B., Wang, J.: Confidence regularized self-training. In: ICCV, pp. 5982–5991 (2019)
Acknowledgment
This work is supported by the National Natural Science Foundation of China (Nos. 61966004,61866004), the Guangxi Natural Science Foundation (No. 2019GXNSFDA245018), the Guangxi “Bagui Scholar” Teams for Innovation and Research Project.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2022 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Li, Z., Li, W., Zhang, J. (2022). Domain Adaptative Semantic Segmentation by Fine-Grained Alignment. In: Pimenidis, E., Angelov, P., Jayne, C., Papaleonidas, A., Aydin, M. (eds) Artificial Neural Networks and Machine Learning – ICANN 2022. ICANN 2022. Lecture Notes in Computer Science, vol 13532. Springer, Cham. https://doi.org/10.1007/978-3-031-15937-4_32
Download citation
DOI: https://doi.org/10.1007/978-3-031-15937-4_32
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-15936-7
Online ISBN: 978-3-031-15937-4
eBook Packages: Computer ScienceComputer Science (R0)