Advertisement

Domain Transfer Through Deep Activation Matching

  • Haoshuo Huang
  • Qixing Huang
  • Philipp Krähenbühl
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 11220)

Abstract

We introduce a layer-wise unsupervised domain adaptation approach for semantic segmentation. Instead of merely matching the output distributions of the source and target domains, our approach aligns the distributions of activations of intermediate layers. This scheme exhibits two key advantages. First, matching across intermediate layers introduces more constraints for training the network in the target domain, making the optimization problem better conditioned. Second, the matched activations at each layer provide similar inputs to the next layer for both training and adaptation, and thus alleviate covariate shift. We use a Generative Adversarial Network (or GAN) to align activation distributions. Experimental results show that our approach achieves state-of-the-art results on a variety of popular domain adaptation tasks, including (1) from GTA to Cityscapes for semantic segmentation, (2) from SYNTHIA to Cityscapes for semantic segmentation, and (3) adaptations on USPS and MNIST for image classification (The website of this paper is https://rsents.github.io/dam.html).

Keywords

Domain adaptation Image classification Semantic segmentation Activation matching GTA SYNTHIA Cityscapes USPS and MNIST 

Notes

Acknowledgment

We would like to thank Angela Lin, and Thomas Crosley for their valuable comments and feedback on this paper. This work was supported in part by Berkeley DeepDrive and an equipment grant from Nvidia.

References

  1. 1.
    Tzeng, E., Hoffman, J., Saenko, K., Darrell, T.: Adversarial discriminative domain adaptation. In: CVPR (2017)Google Scholar
  2. 2.
    Goodfellow, I., et al.: Generative adversarial nets. In: NIPS (2014)Google Scholar
  3. 3.
    Panareda Busto, P., Gall, J.: Open set domain adaptation. In: ICCV (2017)Google Scholar
  4. 4.
    Gebru, T., Hoffman, J., Fei-Fei, L.: Fine-grained recognition in the wild: a multi-task domain adaptation approach. In: ICCV (2017)Google Scholar
  5. 5.
    Zhang, Y., David, P., Gong, B.: Curriculum domain adaptation for semantic segmentation of urban scenes. In: ICCV (2017)Google Scholar
  6. 6.
    Gholami, B., (Oggi) Rudovic, O., Pavlovic, V.: Punda: Probabilistic unsupervised domain adaptation for knowledge transfer across visual categories. In: ICCV (2017)Google Scholar
  7. 7.
    Maria Carlucci, F., Porzi, L., Caputo, B., Ricci, E., Rota Bulo, S.: Autodial: automatic domain alignment layers. In: ICCV (2017)Google Scholar
  8. 8.
    Yan, H., Ding, Y., Li, P., Wang, Q., Xu, Y., Zuo, W.: Mind the class weight bias: weighted maximum mean discrepancy for unsupervised domain adaptation. In: CVPR (2017)Google Scholar
  9. 9.
    Bousmalis, K., Silberman, N., Dohan, D., Erhan, D., Krishnan, D.: Unsupervised pixel-level domain adaptation with generative adversarial networks. In: CVPR (2017)Google Scholar
  10. 10.
    Herath, S., Harandi, M., Porikli, F.: Learning an invariant Hilbert space for domain adaptation. In: CVPR (2017)Google Scholar
  11. 11.
    Koniusz, P., Tas, Y., Porikli, F.: Domain adaptation by mixture of alignments of second- or higher-order scatter tensors. In: CVPR (2017)Google Scholar
  12. 12.
    Sankaranarayanan, S., Balaji, Y., Castillo, C.D., Chellappa, R.: Generate to adapt: aligning domains using generative adversarial networks. In: CVPR (2018)Google Scholar
  13. 13.
    Patel, V.M., Gopalan, R., Li, R., Chellappa, R.: Visual domain adaptation: a survey of recent advances. IEEE Signal Process. Mag. (2015)Google Scholar
  14. 14.
    Csurka, G.: Domain adaptation for visual applications: a comprehensive survey. arXiv preprint arXiv:1702.05374 (2017)
  15. 15.
    Saenko, K., Kulis, B., Fritz, M., Darrell, T.: Adapting visual category models to new domains. In: ECCV (2010)Google Scholar
  16. 16.
    Tzeng, E., Hoffman, J., Zhang, N., Saenko, K., Darrell, T.: Deep domain confusion: maximizing for domain invariance. In: CoRR (2014)Google Scholar
  17. 17.
    Long, J., Shelhamer, E., Darrell, T.: Fully convolutional networks for semantic segmentation. In: CVPR. IEEE Computer Society (2015)Google Scholar
  18. 18.
    Ganin, Y., et al.: Domain-adversarial training of neural networks. JMLR (2016)Google Scholar
  19. 19.
    Tzeng, E., Hoffman, J., Darrell, T., Saenko, K.: Simultaneous deep transfer across domains and tasks. In: ICCV (2015)Google Scholar
  20. 20.
    Liu, M.Y., Tuzel, O.: Coupled generative adversarial networks. In: NIPS (2016)Google Scholar
  21. 21.
    Ghifary, M., Kleijn, W.B., Zhang, M., Balduzzi, D., Li, W.: Deep reconstruction-classification networks for unsupervised domain adaptation. In: ECCV (2016)Google Scholar
  22. 22.
    Isola, P., Zhu, J., Zhou, T., Efros, A.A.: Image-to-image translation with conditional adversarial networks. In: CVPR (2017)Google Scholar
  23. 23.
    Sangkloy, P., Lu, J., Fang, C., Yu, F., Hays, J.: Scribbler: Controlling deep image synthesis with sketch and color. In: CVPR (2017)Google Scholar
  24. 24.
    Karacan, L., Akata, Z., Erdem, A., Erdem, E.: Learning to generate images of outdoor scenes from attributes and semantic layouts. In: CoRR (2016)Google Scholar
  25. 25.
    Yoo, D., Kim, N., Park, S., Paek, A.S., Kweon, I.S.: Pixel-level domain transfer. In: ECCV (2016)Google Scholar
  26. 26.
    Taigman, Y., Polyak, A., Wolf, L.: Unsupervised cross-domain image generation. In: ICLR (2017)Google Scholar
  27. 27.
    Shrivastava, A., Pfister, T., Tuzel, O., Susskind, J., Wang, W., Webb, R.: Learning from simulated and unsupervised images through adversarial training. In: CVPR (2017)Google Scholar
  28. 28.
    Zhu, J.Y., Park, T., Isola, P., Efros, A.A.: Unpaired image-to-image translation using cycle-consistent adversarial networks. In: ICCV (2017)Google Scholar
  29. 29.
    Yi, Z., Zhang, H., Tan, P., Gong, M.: Dualgan: Unsupervised dual learning for image-to-image translation. In: ICCV (2017)Google Scholar
  30. 30.
    Hoffman, J., et al.: Cycada: Cycle-consistent adversarial domain adaptation. In: ICML (2018)Google Scholar
  31. 31.
    Levinkov, E., Fritz, M.: Sequential bayesian model update under structured scene prior for semantic road scenes labeling. In: ICCV (2013)Google Scholar
  32. 32.
    Hoffman, J., Wang, D., Yu, F., Darrell, T.: Fcns in the wild: pixel-level adversarial and constraint-based adaptation. In: CoRR. arXiv:abs/1612.02649 (2016)
  33. 33.
    Ros, G., Stent, S., Alcantarilla, P.F., Watanabe, T.: Training constrained deconvolutional networks for road scene semantic segmentation. In: CoRR. arXiv:abs/1604.01545 (2016)
  34. 34.
    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)Google Scholar
  35. 35.
    Glorot, X., Bengio, Y.: Understanding the difficulty of training deep feedforward neural networks. In: AIStats (2010)Google Scholar
  36. 36.
    Li, Y., Wang, N., Shi, J., Liu, J., Hou, X.: Revisiting batch normalization for practical domain adaptation. In: ICLR (2017)Google Scholar
  37. 37.
    Mao, X., Li, Q., Xie, H., Lau, R.Y.K., Wang, Z.: Multi-class generative adversarial networks with the L2 loss function. In: CoRR (2016)Google Scholar
  38. 38.
    LeCun, Y., Bottou, L., Bengio, Y., Haffner, P.: Gradient-based learning applied to document recognition. In: Proceedings of the IEEE (1998)Google Scholar
  39. 39.
    Netzer, Y., Wang, T., Coates, A., Bissacco, A., Wu, B., Ng, A.Y.: Reading digits in natural images with unsupervised feature learning. In: NIPS Deep Learning Workshop (2011)Google Scholar
  40. 40.
    Cordts, M., et al.: The cityscapes dataset for semantic urban scene understanding. In: CVPR (2016)Google Scholar
  41. 41.
    Paszke, A., Chaurasia, A., Kim, S., Culurciello, E.: Enet: a deep neural network architecture for real-time semantic segmentation. In: CoRR (2016)Google Scholar
  42. 42.
    Ros, G., Sellart, L., Materzynska, J., Vazquez, D., Lopez, A.: The SYNTHIA dataset: a large collection of synthetic images for semantic segmentation of urban scenes. In: CVPR (2016)Google Scholar
  43. 43.
    Long, M., Wang, J., Jordan, M.I.: Deep transfer learning with joint adaptation networks. In: ICML (2016)Google Scholar
  44. 44.
    Yu, F., Koltun, V., Funkhouser, T.: Dilated residual networks. In: CVPR (2017)Google Scholar

Copyright information

© Springer Nature Switzerland AG 2018

Authors and Affiliations

  1. 1.Tsinghua UniversityBeijingChina
  2. 2.University of Texas at AustinAustinUSA

Personalised recommendations