Abstract
Unsupervised Domain Adaptation (UDA) for semantic segmentation has been widely studied to exploit the label-rich source data to assist the segmentation of unlabeled samples on target domain. Despite these efforts, UDA performance remains far below that of fully-supervised model owing to the lack of target annotations. To this end, we propose an efficient superpixel-level active learning method for domain adaptive semantic segmentation to maximize segmentation performance by automatically querying a small number of superpixels for labeling. To conserve annotation resources, we propose a novel low-uncertainty superpixel fusion module which amalgamates superpixels possessing low-uncertainty features based on feature affinity and thereby ensuring high-quality fusion of superpixels. As for the acquisition strategy, our method takes into account two types of information-rich superpixels: large-size superpixels with substantial information content, and superpixels with the greatest value for domain adaptation learning. Further, we employ the cross-domain mixing and pseudo label with consistency regularization techniques respectively to address the domain shift and label noise problems. Extensive experimentation demonstrates that our proposed superpixel-level method utilizes a limited budget more efficiently than previous pixel-level techniques and surpasses state-of-the-art methods at 40x lower cost. Our code is available at https://github.com/EdenHazardan/ADA_superpixel.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Similar content being viewed by others
References
Achanta, R., Shaji, A., Smith, K., Lucchi, A., Fua, P., Süsstrunk, S.: Slic superpixels compared to state-of-the-art superpixel methods. TPAMI (2012)
Van den Bergh, M., Boix, X., Roig, G., De Capitani, B., Van Gool, L.: Seeds: superpixels extracted via energy-driven sampling. In: ECCV (2012)
Cai, L., Xu, X., Liew, J.H., Foo, C.S.: Revisiting superpixels for active learning in semantic segmentation with realistic annotation costs. In: CVPR (2021)
Casanova, A., Pinheiro, P.O., Rostamzadeh, N., Pal, C.J.: Reinforced active learning for image segmentation. arXiv preprint arXiv:2002.06583 (2020)
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 (2017)
Chen, L.C., Zhu, Y., Papandreou, G., Schroff, F., Adam, H.: Encoder-decoder with atrous separable convolution for semantic image segmentation. In: ECCV (2018)
Chen, L., Wei, Z., Jin, X., Chen, H., Zheng, M., Chen, K., Jin, Y.: Deliberated domain bridging for domain adaptive semantic segmentation. NeurIPS (2022)
Cheng, Y., Wei, F., Bao, J., Chen, D., Wen, F., Zhang, W.: Dual path learning for domain adaptation of semantic segmentation. In: ICCV (2021)
Colling, P., Roese-Koerner, L., Gottschalk, H., Rottmann, M.: Metabox+: A new region based active learning method for semantic segmentation using priority maps. arXiv preprint arXiv:2010.01884 (2020)
Cordts, M., et al.: The cityscapes dataset for semantic urban scene understanding. In: CVPR (2016)
Culotta, A., McCallum, A.: Reducing labeling effort for structured prediction tasks. In: AAAI (2005)
Everingham, M., Van Gool, L., Williams, C.K., Winn, J., Zisserman, A.: The pascal visual object classes (voc) challenge. IJCV (2010)
Gao, Y., Wang, Z., Zhuang, J., Zhang, Y., Li, J.: Exploit domain-robust optical flow in domain adaptive video semantic segmentation. In: AAAI (2023)
Hoyer, L., Dai, D., Van Gool, L.: Daformer: Improving network architectures and training strategies for domain-adaptive semantic segmentation. In: CVPR (2022)
Jampani, V., Sun, D., Liu, M.Y., Yang, M.H., Kautz, J.: Superpixel sampling networks. In: ECCV (2018)
Joshi, A.J., Porikli, F., Papanikolopoulos, N.: Multi-class active learning for image classification. In: CVPR. IEEE (2009)
Kim, H., Oh, M., Hwang, S., Kwak, S., Ok, J.: Adaptive superpixel for active learning in semantic segmentation. In: ICCV (2023)
Koh, K.B., Fernando, B.: Consistency regularization for domain adaptation. In: ECCV (2022)
Lee, S., Choi, W., Kim, C., Choi, M., Im, S.: Adas: a direct adaptation strategy for multi-target domain adaptive semantic segmentation. In: CVPR (2022)
Li, J., Wang, Z., Gao, Y., Hu, X.: Exploring high-quality target domain information for unsupervised domain adaptive semantic segmentation. In: ACM MM (2022)
Li, Z., Chen, J.: Superpixel segmentation using linear spectral clustering. In: CVPR (2015)
Lin, T.Y., et al.: Microsoft coco: common objects in context. In: ECCV (2014)
Liu, Y., Deng, J., Gao, X., Li, W., Duan, L.: Bapa-net: boundary adaptation and prototype alignment for cross-domain semantic segmentation. In: ICCV (2021)
Mackowiak, R., Lenz, P., Ghori, O., Diego, F., Lange, O., Rother, C.: Cereals-cost-effective region-based active learning for semantic segmentation. arXiv preprint arXiv:1810.09726 (2018)
Mei, K., Zhu, C., Zou, J., Zhang, S.: Instance adaptive self-training for unsupervised domain adaptation. In: ECCV (2020)
Melas-Kyriazi, L., Manrai, A.K.: Pixmatch: unsupervised domain adaptation via pixelwise consistency training. In: CVPR (2021)
Milioto, A., Stachniss, C.: Bonnet: An open-source training and deployment framework for semantic segmentation in robotics using CNNs. In: ICRA (2019)
Ning, M., et al.: Multi-anchor active domain adaptation for semantic segmentation. In: ICCV (2021)
Richter, S.R., Vineet, V., Roth, S., Koltun, V.: Playing for data: ground truth from computer games. In: ECCV. Springer (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 (2016)
Shin, I., Kim, D.J., Cho, J.W., Woo, S., Park, K., Kweon, I.S.: Labor: labeling only if required for domain adaptive semantic segmentation. In: Proceedings of the IEEE/CVF International Conference on Computer Vision, pp. 8588–8598 (2021)
Siam, M., Gamal, M., Abdel-Razek, M., Yogamani, S., Jagersand, M., Zhang, H.: A comparative study of real-time semantic segmentation for autonomous driving. In: CVPR workshops (2018)
Sohn, K., et al.: Fixmatch: simplifying semi-supervised learning with consistency and confidence. NeurIPS (2020)
Sumithra, R., Suhil, M., Guru, D.: Segmentation and classification of skin lesions for disease diagnosis. Procedia Comput. Sci. (2015)
Tranheden, W., Olsson, V., Pinto, J., Svensson, L.: Dacs: domain adaptation via cross-domain mixed sampling. In: WACV (2021)
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, D., Shang, Y.: A new active labeling method for deep learning. In: 2014 International joint conference on neural networks (IJCNN). IEEE (2014)
Wang, Q., Dai, D., Hoyer, L., Van Gool, L., Fink, O.: Domain adaptive semantic segmentation with self-supervised depth estimation. In: ICCV (2021)
Wu, T.H., et al.: D 2 ada: dynamic density-aware active domain adaptation for semantic segmentation. In: ECCV (2022)
Xie, B., Yuan, L., Li, S., Liu, C.H., Cheng, X.: Towards fewer annotations: active learning via region impurity and prediction uncertainty for domain adaptive semantic segmentation. In: CVPR (2022)
Xie, E., Wang, W., Yu, Z., Anandkumar, A., Alvarez, J.M., Luo, P.: Segformer: simple and efficient design for semantic segmentation with transformers. NeurIPS (2021)
Yang, F., Sun, Q., Jin, H., Zhou, Z.: Superpixel segmentation with fully convolutional networks. In: CVPR (2020)
Yang, L., Zhuo, W., Qi, L., Shi, Y., Gao, Y.: St++: make self-training work better for semi-supervised semantic segmentation. In: CVPR (2022)
You, F., Li, J., Chen, Z., Zhu, L.: Pixel exclusion: uncertainty-aware boundary discovery for active cross-domain semantic segmentation. In: ACM MM (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, Y., Wang, Z.: Joint adversarial learning for domain adaptation in semantic segmentation. In: AAAI (2020)
Acknowledgements
This work is supported by the National Natural Science Foundation of China under Grant 62176246. This work is also supported by Anhui Province Key Research and Development Plan (202304a05020045) and Anhui Province Natural Science Foundation (2208085UD17).
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2025 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Gao, Y., Wang, Z., Zhang, Y., Tu, B. (2025). Efficient Active Domain Adaptation for Semantic Segmentation by Selecting Information-Rich Superpixels. In: Leonardis, A., Ricci, E., Roth, S., Russakovsky, O., Sattler, T., Varol, G. (eds) Computer Vision – ECCV 2024. ECCV 2024. Lecture Notes in Computer Science, vol 15092. Springer, Cham. https://doi.org/10.1007/978-3-031-72754-2_23
Download citation
DOI: https://doi.org/10.1007/978-3-031-72754-2_23
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-72753-5
Online ISBN: 978-3-031-72754-2
eBook Packages: Computer ScienceComputer Science (R0)