Skip to main content

Label-Driven Reconstruction for Domain Adaptation in Semantic Segmentation

Part of the Lecture Notes in Computer Science book series (LNIP,volume 12372)

Abstract

Unsupervised domain adaptation enables to alleviate the need for pixel-wise annotation in the semantic segmentation. One of the most common strategies is to translate images from the source domain to the target domain and then align their marginal distributions in the feature space using adversarial learning. However, source-to-target translation enlarges the bias in translated images and introduces extra computations, owing to the dominant data size of the source domain. Furthermore, consistency of the joint distribution in source and target domains cannot be guaranteed through global feature alignment. Here, we present an innovative framework, designed to mitigate the image translation bias and align cross-domain features with the same category. This is achieved by 1) performing the target-to-source translation and 2) reconstructing both source and target images from their predicted labels. Extensive experiments on adapting from synthetic to real urban scene understanding demonstrate that our framework competes favorably against existing state-of-the-art methods.

Keywords

  • Image-to-image translation
  • Image reconstruction
  • Domain adaptation
  • Semantic segmentation

This is a preview of subscription content, access via your institution.

Buying options

Chapter
USD   29.95
Price excludes VAT (USA)
  • DOI: 10.1007/978-3-030-58583-9_29
  • Chapter length: 19 pages
  • Instant PDF download
  • Readable on all devices
  • Own it forever
  • Exclusive offer for individuals only
  • Tax calculation will be finalised during checkout
eBook
USD   109.00
Price excludes VAT (USA)
  • ISBN: 978-3-030-58583-9
  • Instant PDF download
  • Readable on all devices
  • Own it forever
  • Exclusive offer for individuals only
  • Tax calculation will be finalised during checkout
Softcover Book
USD   149.99
Price excludes VAT (USA)
Fig. 1.
Fig. 2.
Fig. 3.
Fig. 4.
Fig. 5.

References

  1. Cycada: Cycle consistent adversarial domain adaptation. In: International Conference on Machine Learning (ICML) (2018)

    Google Scholar 

  2. Bousmalis, K., Trigeorgis, G., Silberman, N., Krishnan, D., Erhan, D.: Domain separation networks. In: Advances in Neural Information Processing Systems (NIPS), pp. 343–351 (2016)

    Google Scholar 

  3. 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: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 1900–1909 (2019)

    Google Scholar 

  4. Chen, L.C., et al.: Searching for efficient multi-scale architectures for dense image prediction. In: Advances in Neural Information Processing Systems (NIPS) (2018)

    Google Scholar 

  5. Chen, L.C., Papandreou, G., Kokkinos, I., Murphy, K., Yuille, A.L.: Semantic image segmentation with deep convolutional nets and fully connected CRFs. In: International Conference on Learning Representations (ICLR) (2014)

    Google Scholar 

  6. 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. IEEE Trans. Pattern Anal. Mach. Intell. (TPAMI) 40(4), 834–848 (2018)

    CrossRef  Google Scholar 

  7. Chen, Y., Li, W., Chen, X., Gool, L.V.: Learning semantic segmentation from synthetic data: a geometrically guided input-output adaptation approach. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 1841–1850 (2019)

    Google Scholar 

  8. Chen, Y., Li, W., Van Gool, L.: Road: reality oriented adaptation for semantic segmentation of urban scenes. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 7892–7901 (2018)

    Google Scholar 

  9. Chen, Y.C., Lin, Y.Y., Yang, M.H., Huang, J.B.: Crdoco: pixel-level domain transfer with cross-domain consistency. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 1791–1800 (2019)

    Google Scholar 

  10. Choi, J., Kim, T., Kim, C.: Self-ensembling with GAN-based data augmentation for domain adaptation in semantic segmentation. In: Proceedings of the IEEE International Conference on Computer Vision (ICCV) (2019)

    Google Scholar 

  11. Cordts, M., et al.: The cityscapes dataset for semantic urban scene understanding. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 3213–3223 (2016)

    Google Scholar 

  12. Dai, J., He, K., Sun, J.: Boxsup: exploiting bounding boxes to supervise convolutional networks for semantic segmentation. In: Proceedings of the IEEE International Conference on Computer Vision (ICCV), pp. 1635–1643 (2015)

    Google Scholar 

  13. Du, L., et al.: Ssf-dan: separated semantic feature based domain adaptation network for semantic segmentation. In: Proceedings of the IEEE International Conference on Computer Vision (ICCV) (2019)

    Google Scholar 

  14. Everingham, M., Van Gool, L., Williams, C.K.I., Winn, J., Zisserman, A.: The PASCAL Visual Object Classes Challenge (VOC2012) Results (2012). http://www.pascal-network.org/challenges/VOC/voc2012/workshop/index.html

  15. Ganin, Y., Lempitsky, V.: Unsupervised domain adaptation by backpropagation. In: International Conference on Machine Learning (ICML) (2015)

    Google Scholar 

  16. Ghifary, M., Kleijn, W.B., Zhang, M., Balduzzi, D., Li, W.: Deep reconstruction-classification networks for unsupervised domain adaptation. In: Proceedings of the European Conference on Computer Vision (ECCV), pp. 597–613 (2016)

    Google Scholar 

  17. Girshick, R.: Fast r-cnn. In: Proceedings of the IEEE International Conference on Computer Vision (ICCV), pp. 1440–1448 (2015)

    Google Scholar 

  18. Goodfellow, I.: Nips 2016 tutorial: generative adversarial networks. arXiv preprint arXiv:1701.00160 (2016)

  19. Goodfellow, I., et al.: Generative adversarial nets. In: Advances in Neural Information Processing Systems (NIPS), pp. 2672–2680 (2014)

    Google Scholar 

  20. He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 770–778 (2016)

    Google Scholar 

  21. 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)

  22. Huang, J., Lu, S., Guan, D., Zhang, X.: Contextual-relation consistent domain adaptation for semantic segmentation. In: Proceedings of the European Conference on Computer Vision (ECCV) (2020)

    Google Scholar 

  23. Isola, P., Zhu, J.Y., Zhou, T., Efros, A.A.: Image-to-image translation with conditional adversarial networks. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 1125–1134 (2017)

    Google Scholar 

  24. Johnson, J., Alahi, A., Fei-Fei, L.: Perceptual losses for real-time style transfer and super-resolution. In: Proceedings of the European Conference on Computer Vision (ECCV), pp. 694–711 (2016)

    Google Scholar 

  25. Kim, M., Byun, H.: Learning texture invariant representation for domain adaptation of semantic segmentation. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 12975–12984 (2020)

    Google Scholar 

  26. Kingma, D.P., Ba, J.: Adam: a method for stochastic optimization. In: International Conference on Learning Representations (ICLR) (2014)

    Google Scholar 

  27. Lee, K.H., Ros, G., Li, J., Gaidon, A.: Spigan: privileged adversarial learning from simulation. In: International Conference on Learning Representations (ICLR) (2019)

    Google Scholar 

  28. Li, Y., Yuan, L., Vasconcelos, N.: Bidirectional learning for domain adaptation of semantic segmentation. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2019)

    Google Scholar 

  29. Lian, Q., Lv, F., Duan, L., Gong, B.: Constructing self-motivated pyramid curriculums for cross-domain semantic segmentation: a non-adversarial approach. In: Proceedings of the IEEE International Conference on Computer Vision (ICCV) (2019)

    Google Scholar 

  30. Liu, M.Y., Breuel, T., Kautz, J.: Unsupervised image-to-image translation networks. In: Advances in Neural Information Processing Systems (NIPS), pp. 700–708 (2017)

    Google Scholar 

  31. Liu, Z., Li, X., Luo, P., Loy, C.C., Tang, X.: Semantic image segmentation via deep parsing network. In: Proceedings of the IEEE International Conference on Computer Vision (ICCV), pp. 1377–1385 (2015)

    Google Scholar 

  32. Long, J., Shelhamer, E., Darrell, T.: Fully convolutional networks for semantic segmentation. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 3431–3440 (2015)

    Google Scholar 

  33. Long, M., Cao, Y., Wang, J., Jordan, M.I.: Learning transferable features with deep adaptation networks. In: International Conference on Machine Learning (ICML) (2015)

    Google Scholar 

  34. Luo, Y., Liu, P., Guan, T., Yu, J., Yang, Y.: Significance-aware information bottleneck for domain adaptive semantic segmentation. In: Proceedings of the IEEE International Conference on Computer Vision (ICCV) (2019)

    Google Scholar 

  35. 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: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 2507–2516 (2019)

    Google Scholar 

  36. Murez, Z., Kolouri, S., Kriegman, D., Ramamoorthi, R., Kim, K.: Image to image translation for domain adaptation. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 4500–4509 (2018)

    Google Scholar 

  37. Murez, Z., Kolouri, S., Kriegman, D., Ramamoorthi, R., Kim, K.: Image to image translation for domain adaptation. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), vol. 13 (2018)

    Google Scholar 

  38. Pan, F., Shin, I., Rameau, F., Lee, S., Kweon, I.S.: Unsupervised intra-domain adaptation for semantic segmentation through self-supervision. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 3764–3773 (2020)

    Google Scholar 

  39. Paszke, A., et al.: Automatic differentiation in pytorch (2017)

    Google Scholar 

  40. Pinheiro, P.O., Collobert, R.: From image-level to pixel-level labeling with convolutional networks. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 1713–1721 (2015)

    Google Scholar 

  41. Richter, S.R., Vineet, V., Roth, S., Koltun, V.: Playing for data: ground truth from computer games. In: Proceedings of the European Conference on Computer Vision (ECCV), pp. 102–118 (2016)

    Google Scholar 

  42. 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: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 3234–3243 (2016)

    Google Scholar 

  43. Sankaranarayanan, S., Balaji, Y., Jain, A., Lim, S.N., Chellappa, R.: Learning from synthetic data: addressing domain shift for semantic segmentation. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2018)

    Google Scholar 

  44. Simonyan, K., Zisserman, A.: Very deep convolutional networks for large-scale image recognition. In: International Conference on Learning Representations (ICLR) (2015)

    Google Scholar 

  45. 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: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2018)

    Google Scholar 

  46. Tzeng, E., Hoffman, J., Darrell, T., Saenko, K.: Simultaneous deep transfer across domains and tasks. In: Proceedings of the IEEE International Conference on Computer Vision (ICCV), pp. 4068–4076 (2015)

    Google Scholar 

  47. Tzeng, E., Hoffman, J., Saenko, K., Darrell, T.: Adversarial discriminative domain adaptation. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2017)

    Google Scholar 

  48. Tzeng, E., Hoffman, J., Zhang, N., Saenko, K., Darrell, T.: Deep domain confusion: Maximizing for domain invariance. arXiv preprint arXiv:1412.3474 (2014)

  49. Vu, T.H., Jain, H., Bucher, M., Cord, M., Pérez, P.: Dada: depth-aware domain adaptation in semantic segmentation. In: Proceedings of the IEEE International Conference on Computer Vision (ICCV) (2019)

    Google Scholar 

  50. Wang, T.C., Liu, M.Y., Zhu, J.Y., Tao, A., Kautz, J., Catanzaro, B.: High-resolution image synthesis and semantic manipulation with conditional GANs. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2017)

    Google Scholar 

  51. Wang, Z., et al.: Differential treatment for stuff and things: a simple unsupervised domain adaptation method for semantic segmentation. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 12635–12644 (2020)

    Google Scholar 

  52. Wu, Z., et al.: Dcan: dual channel-wise alignment networks for unsupervised scene adaptation. In: Proceedings of the European Conference on Computer Vision (ECCV), pp. 518–534 (2018)

    Google Scholar 

  53. Yang, J., An, W., Yan, C., Zhao, P., Huang, J.: Context-aware domain adaptation in semantic segmentation. arXiv preprint arXiv:2003.04010 (2020)

  54. Yang, Y., Soatto, S.: Fda: fourier domain adaptation for semantic segmentation. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 4085–4095 (2020)

    Google Scholar 

  55. Ying, W., Zhang, Y., Huang, J., Yang, Q.: Transfer learning via learning to transfer. In: International Conference on Machine Learning (ICML), pp. 5072–5081 (2018)

    Google Scholar 

  56. Zhang, Y., David, P., Gong, B.: Curriculum domain adaptation for semantic segmentation of urban scenes. In: Proceedings of the IEEE International Conference on Computer Vision (ICCV) (2017)

    Google Scholar 

  57. Zhang, Y., et al.: Collaborative unsupervised domain adaptation for medical image diagnosis. IEEE Trans. Image Process. (TIP) 29, 7834–7844 (2020)

    CrossRef  Google Scholar 

  58. Zhang, Y., Qiu, Z., Yao, T., Liu, D., Mei, T.: Fully convolutional adaptation networks for semantic segmentation. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 6810–6818 (2018)

    Google Scholar 

  59. Zhao, H., Shi, J., Qi, X., Wang, X., Jia, J.: Pyramid scene parsing network. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 2881–2890 (2017)

    Google Scholar 

  60. Zhu, J.Y., Park, T., Isola, P., Efros, A.A.: Unpaired image-to-image translation using cycle-consistent adversarial networks. In: Proceedings of the IEEE International Conference on Computer Vision (ICCV) (2017)

    Google Scholar 

  61. Zhu, X., Zhou, H., Yang, C., Shi, J., Lin, D.: Penalizing top performers: conservative loss for semantic segmentation adaptation. In: Proceedings of the European Conference on Computer Vision (ECCV), pp. 568–583 (2018)

    Google Scholar 

  62. 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

    CrossRef  Google Scholar 

Download references

Acknowledgments

This work was partially supported by US National Science Foundation IIS-1718853, the CAREER grant IIS-1553687 and Cancer Prevention and Research Institute of Texas (CPRIT) award (RP190107).

Author information

Authors and Affiliations

Authors

Corresponding author

Correspondence to Junzhou Huang .

Editor information

Editors and Affiliations

1 Electronic supplementary material

Below is the link to the electronic supplementary material.

Supplementary material 1 (pdf 3662 KB)

Rights and permissions

Reprints and Permissions

Copyright information

© 2020 Springer Nature Switzerland AG

About this paper

Verify currency and authenticity via CrossMark

Cite this paper

Yang, J., An, W., Wang, S., Zhu, X., Yan, C., Huang, J. (2020). Label-Driven Reconstruction for Domain Adaptation in Semantic Segmentation. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, JM. (eds) Computer Vision – ECCV 2020. ECCV 2020. Lecture Notes in Computer Science(), vol 12372. Springer, Cham. https://doi.org/10.1007/978-3-030-58583-9_29

Download citation

  • DOI: https://doi.org/10.1007/978-3-030-58583-9_29

  • Published:

  • Publisher Name: Springer, Cham

  • Print ISBN: 978-3-030-58582-2

  • Online ISBN: 978-3-030-58583-9

  • eBook Packages: Computer ScienceComputer Science (R0)