Abstract
Learning semantic segmentation models requires a huge amount of pixel-wise labeling. However, labeled data may only be available abundantly in a domain different from the desired target domain, which only has minimal or no annotations. In this work, we propose a novel framework for domain adaptation in semantic segmentation with image-level weak labels in the target domain. The weak labels may be obtained based on a model prediction for unsupervised domain adaptation (UDA), or from a human annotator in a new weakly-supervised domain adaptation (WDA) paradigm for semantic segmentation. Using weak labels is both practical and useful, since (i) collecting image-level target annotations is comparably cheap in WDA and incurs no cost in UDA, and (ii) it opens the opportunity for category-wise domain alignment. Our framework uses weak labels to enable the interplay between feature alignment and pseudo-labeling, improving both in the process of domain adaptation. Specifically, we develop a weak-label classification module to enforce the network to attend to certain categories, and then use such training signals to guide the proposed category-wise alignment method. In experiments, we show considerable improvements with respect to the existing state-of-the-arts in UDA and present a new benchmark in the WDA setting. Project page is at http://www.nec-labs.com/~mas/WeakSegDA.
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
Similar content being viewed by others
References
Ahn, J., Kwak, S.: Learning pixel-level semantic affinity with image-level supervision for weakly supervised semantic segmentation. In: CVPR (2018)
Bearman, A., Russakovsky, O., Ferrari, V., Fei-Fei, L.: What’s the point: semantic segmentation with point supervision. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016. LNCS, vol. 9911, pp. 549–565. Springer, Cham (2016). https://doi.org/10.1007/978-3-319-46478-7_34
Bousmalis, K., Silberman, N., Dohan, D., Erhan, D., Krishnan, D.: Unsupervised pixel-level domain adaptation with generative adversarial networks. In: CVPR (2017)
Chang, W.L., Wang, H.P., Peng, W.H., Chiu, W.C.: All about structure: adapting structural information across domains for boosting semantic segmentation. In: CVPR (2019)
Chang, Y.T., Wang, Q., Hung, W.C., Piramuthu, R., Tsai, Y.H., Yang, M.H.: Weakly-supervised semantic segmentation via sub-category exploration. In: CVPR (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. CoRR abs/1606.00915 (2016)
Chen, Y.H., Chen, W.Y., Chen, Y.T., Tsai, B.C., Wang, Y.C.F., Sun, M.: No more discrimination: cross city adaptation of road scene segmenters. In: ICCV (2017)
Chen, Y.W., Tsai, Y.H., Lin, Y.Y., Yang, M.H.: VOSTR: video object segmentation via transferable representations. Int. J. Comput. Vis. (2020)
Chen, Y., Li, W., Gool, L.V.: ROAD: reality oriented adaptation for semantic segmentation of urban scenes. In: CVPR (2018)
Choi, J., Kim, T., Kim, C.: Self-ensembling with GAN-based data augmentation for domain adaptation in semantic segmentation. In: ICCV (2019)
Cordts, M., et al.: The cityscapes dataset for semantic urban scene understanding. In: CVPR (2016)
Dai, J., He, K., Sun, J.: BoxSup: exploiting bounding boxes to supervise convolutional networks for semantic segmentation. In: ICCV (2015)
Dai, S., Sohn, K., Tsai, Y.H., Carin, L., Chandraker, M.: Adaptation across extreme variations using unlabeled domain bridges. ar**v preprint ar**v:1906.02238 (2019)
Du, L., et al.: SSF-DAN: separated semantic feature based domain adaptation network for semantic segmentation. In: ICCV (2019)
Fernando, B., Habrard, A., Sebban, M., Tuytelaars, T.: Unsupervised visual domain adaptation using subspace alignment. In: ICCV (2013)
Ganin, Y., Lempitsky, V.: Unsupervised domain adaptation by backpropagation. In: ICML (2015)
Ganin, Y., et al.: Domain-adversarial training of neural networks. In: JMLR (2016)
Gong, B., Shi, Y., Sha, F., Grauman, K.: Geodesic flow kernel for unsupervised domain adaptation. In: CVPR (2012)
Goodfellow, I.J., et al.: Generative adversarial nets. In: NIPS (2014)
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)
Hoffman, J., Wang, D., Yu, F., Darrell, T.: FCNs in the wild: pixel-level adversarial and constraint-based adaptation. CoRR abs/1612.02649 (2016)
Hung, W.C., Tsai, Y.H., Liou, Y.T., Lin, Y.Y., Yang, M.H.: Adversarial learning for semi-supervised semantic segmentation. In: BMVC (2018)
Inoue, N., Furuta, R., Yamasaki, T., Aizawa, K.: Cross-domain weakly-supervised object detection through progressive domain adaptation. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 5001–5009 (2018)
Khoreva, A., Benenson, R., Hosang, J., Hein, M., Schiele, B.: Simple does it: weakly supervised instance and semantic segmentation. In: CVPR (2017)
Kingma, D.P., Ba, J.: Adam: a method for stochastic optimization. In: ICLR (2015)
Kolesnikov, A., Lampert, C.H.: Seed, expand and constrain: three principles for weakly-supervised image segmentation. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016. LNCS, vol. 9908, pp. 695–711. Springer, Cham (2016). https://doi.org/10.1007/978-3-319-46493-0_42
Lee, C.Y., Batra, T., Baig, M.H., Ulbricht, D.: Sliced Wasserstein discrepancy for unsupervised domain adaptation. In: CVPR (2019)
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: ICCV (2019)
Lin, D., Dai, J., Jia, J., He, K., Sun, J.: ScribbleSup: scribble-supervised convolutional networks for semantic segmentation. In: CVPR (2016)
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. In: NIPS (2016)
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)
Murez, Z., Kolouri, S., Kriegman, D., Ramamoorthi, R., Kim, K.: Image to image translation for domain adaptation. In: CVPR (2018)
Papandreou, G., Chen, L.C., Murphy, K., Yuille, A.L.: Weakly-and semi-supervised learning of a DCNN for semantic image segmentation. In: ICCV (2015)
Pathak, D., Krahenbuhl, P., Darrell, T.: Constrained convolutional neural networks for weakly supervised segmentation. In: ICCV (2015)
Pinheiro, P.O., Collobert, R.: From image-level to pixel-level labeling with convolutional networks. In: CVPR (2015)
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 (2016)
Saito, K., Watanabe, K., Ushiku, Y., Harada, T.: Maximum classifier discrepancy for unsupervised domain adaptation. In: CVPR (2018)
Saleh, F.S., Aliakbarian, M.S., Salzmann, M., Petersson, L., Alvarez, J.M.: Bringing background into the foreground: making all classes equal in weakly-supervised video semantic segmentation. In: ICCV (2017)
Saleh, F.S., Aliakbarian, M.S., Salzmann, M., Petersson, L., Alvarez, J.M.: Effective use of synthetic data for urban scene semantic segmentation. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) ECCV 2018. LNCS, vol. 11206, pp. 86–103. Springer, Cham (2018). https://doi.org/10.1007/978-3-030-01216-8_6
Sohn, K., Liu, S., Zhong, G., Yu, X., Yang, M.H., Chandraker, M.: Unsupervised domain adaptation for face recognition in unlabeled videos. In: ICCV (2017)
Sohn, K., Shang, W., Yu, X., Chandraker, M.: Unsupervised domain adaptation for distance metric learning. In: ICLR (2019)
Su, J.C., Tsai, Y.H., Sohn, K., Liu, B., Maji, S., Chandraker, M.: Active adversarial domain adaptation. In: WACV (2020)
Tran, L., Sohn, K., Yu, X., Liu, X., Chandraker, M.: Gotta adapt ’Em all: joint pixel and feature-level domain adaptation for recognition in the wild. In: CVPR (2019)
Tsai, Y.-H., Zhong, G., Yang, M.-H.: Semantic co-segmentation in videos. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016. LNCS, vol. 9908, pp. 760–775. Springer, Cham (2016). https://doi.org/10.1007/978-3-319-46493-0_46
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., Darrell, T., Saenko, K.: Simultaneous deep transfer across domains and tasks. In: ICCV (2015)
Tzeng, E., Hoffman, J., Saenko, K., Darrell, T.: Adversarial discriminative domain adaptation. In: CVPR (2017)
Vernaza, P., Chandraker, M.: Learning random-walk label propagation for weakly-supervised semantic segmentation. In: CVPR (2017)
Vu, T.H., Jain, H., Bucher, M., Cord, M., Pérez, P.: ADVENT: adversarial entropy minimization for domain adaptation in semantic segmentation. In: CVPR (2019)
Vu, T.H., Jain, H., Bucher, M., Cord, M., Pérez, P.: DADA: depth-aware domain adaptation in semantic segmentation. In: ICCV (2019)
Wu, Z., et al.: DCAN: dual channel-wise alignment networks for unsupervised scene adaptation. In: ECCV (2018)
Zhang, Y., David, P., Gong, B.: Curriculum domain adaptation for semantic segmentation of urban scenes. In: ICCV (2017)
Zhang, Y., Qiu, Z., Yao, T., Liu, D., Mei, T.: Fully convolutional adaptation networks for semantic segmentation. In: CVPR (2018)
Zhong, G., Tsai, Y.-H., Yang, M.-H.: Weakly-supervised video scene co-parsing. In: Lai, S.-H., Lepetit, V., Nishino, K., Sato, Y. (eds.) ACCV 2016. LNCS, vol. 10111, pp. 20–36. Springer, Cham (2017). https://doi.org/10.1007/978-3-319-54181-5_2
Zou, Y., Yu, Z., Kumar, B.V.K.V., Wang, J.: Domain adaptation for semantic segmentation via class-balanced self-training. In: ECCV (2018)
Acknowledgement
This work was a part of Sujoy Paul’s internship at NEC Labs America. This work was also partially funded by NSF grant 1724341.
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
Paul, S., Tsai, YH., Schulter, S., Roy-Chowdhury, A.K., Chandraker, M. (2020). Domain Adaptive Semantic Segmentation Using Weak Labels. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, JM. (eds) Computer Vision – ECCV 2020. ECCV 2020. Lecture Notes in Computer Science(), vol 12354. Springer, Cham. https://doi.org/10.1007/978-3-030-58545-7_33
Download citation
DOI: https://doi.org/10.1007/978-3-030-58545-7_33
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-58544-0
Online ISBN: 978-3-030-58545-7
eBook Packages: Computer ScienceComputer Science (R0)