Unsupervised Domain Adaptation with Coupled Generative Adversarial Autoencoders
Source abstract
Abstract
When large-scale annotated data are not available for certain image classification tasks, training a deep convolutional neural network model becomes challenging. Some recent domain adaptation methods try to solve this problem using generative adversarial networks and have achieved promising results. However, these methods are based on a shared latent space assumption and they do not consider the situation when shared high level representations in different domains do not exist or are not ideal as they assumed. To overcome this limitation, we propose a neural network structure called coupled generative adversarial autoencoders (CGAA) that allows a pair of generators to learn the high-level differences between two domains by sharing only part of the high-level layers. Additionally, by introducing a class consistent loss calculated by a stand-alone classifier into the generator optimization, our model is able to generate class invariant style-transferred images suitable for classification tasks in domain adaptation. We apply CGAA to several domain transferred image classification scenarios including several benchmark datasets. Experiment results have shown that our method can achieve state-of-the-art classification results.
Source: crossref · Quality: baseline
Research context
OpenAlex topics: Domain Adaptation and Few-Shot Learning · Multimodal Machine Learning Applications · Cancer-related molecular mechanisms research
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
Affiliations
State Key Laboratory of Precision Measuring Technology and Instruments, Tianjin University, Tianjin 300072, China
Funding
National Natural Science Foundation of China
References (41)
Show source-provided references
1. Lin, T.Y., Maire, M., Belongie, S., Hays, J., Perona, P., Ramanan, D., Dollár, P., and Zitnick, C.L. (2014). Microsoft coco: Common objects in context. European Conference on Computer Vision, Springer.10.1007/978-3-319-10602-1_48 ↗
2. Deng, J., Dong, W., Socher, R., Li, L.J., Li, K., and Fei-Fei, L. (2009, January 20–25). Imagenet: A large-scale hierarchical image database. Proceedings of the 2009 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Miami, FL, USA.10.1109/CVPR.2009.5206848 ↗
3. Geiger, A., Lenz, P., and Urtasun, R. (2012, January 16–21). Are we ready for autonomous driving? the kitti vision benchmark suite. Proceedings of the 2012 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Providence, RI, USA.10.1109/CVPR.2012.6248074 ↗
4. Fernando, B., Habrard, A., Sebban, M., and Tuytelaars, T. (2013, January 1–8). Unsupervised visual domain adaptation using subspace alignment. Proceedings of the 2013 IEEE International Conference on Computer Vision (ICCV), Sydney, NSW, Australia.10.1109/ICCV.2013.368 ↗
5. Gong, B., Shi, Y., Sha, F., and Grauman, K. (2012, January 16–21). Geodesic flow kernel for unsupervised domain adaptation. Proceedings of the 2012 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Providence, RI, USA.
6. Long, M., Wang, J., Ding, G., Sun, J., and Yu, P.S. (2013, January 1–8). Transfer feature learning with joint distribution adaptation. Proceedings of the IEEE International Conference on Computer Vision, Sydney, Australia.10.1109/ICCV.2013.274 ↗
7. Domain adaptation via transfer component analysis10.1109/TNN.2010.2091281 ↗
8. Domain-adversarial training of neural networks
9. Long, M., Cao, Y., Wang, J., and Jordan, M.I. (2015, January 6–11). Learning transferable features with deep adaptation networks. Proceedings of the 32nd International Conference on International Conference on Machine Learning, Lille, France.
10. Temperature drift modeling of mems gyroscope based on genetic-elman neural network
11. Tzeng, E., Hoffman, J., Zhang, N., Saenko, K., and Darrell, T. (arXiv, 2014). Deep domain confusion: Maximizing for domain invariance, arXiv.
12. Ghifary, M., Kleijn, W.B., Zhang, M., Balduzzi, D., and Li, W. (2016). Deep reconstruction-classification networks for unsupervised domain adaptation. European Conference on Computer Vision, Springer.10.1007/978-3-319-46493-0_36 ↗
13. Venkateswara, H., Eusebio, J., Chakraborty, S., and Panchanathan, S. (2017, January 21–26). Deep Hashing Network for Unsupervised Domain Adaptation. Proceedings of the 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Honolulu, HI, USA.10.1109/CVPR.2017.572 ↗
14. Goodfellow, I., Pouget-Abadie, J., Mirza, M., Xu, B., Warde-Farley, D., Ozair, S., Courville, A., and Bengio, Y. (2014, January 8–13). Generative adversarial nets. Proceedings of the Advances in Neural Information Processing Systems, Montreal, QC, Canada.
15. Lee, D.H. (2013, January 21). Pseudo-label: The simple and efficient semi-supervised learning method for deep neural networks. Proceedings of the ICML 2013 Workshop: Challenges in Representation Learning (WREPL), Atlanta, GA, USA.
16. Zheng, Z., Zheng, L., and Yang, Y. (2017, January 22–29). Unlabeled Samples Generated by GAN Improve the Person Re-Identification Baseline in Vitro. Proceedings of the IEEE International Conference on Computer Vision, Venice, Italy.10.1109/ICCV.2017.405 ↗
17. Unsupervised Domain Adaptation for Facial Expression Recognition Using Generative Adversarial Networks10.1155/2018/7208794 ↗
18. Liu, M.Y., and Tuzel, O. (2016, January 5–10). Coupled generative adversarial networks. Proceedings of the Advances in Neural Information Processing Systems (NIPS 2016), Barcelona, Spain.
19. Liu, M.Y., Breuel, T., and Kautz, J. (2017, January 4–9). Unsupervised image-to-image translation networks. Proceedings of the Advances in Neural Information Processing Systems (NIPS 2017), Long Beach, CA, USA.
20. Gradient-based learning applied to document recognition10.1109/5.726791 ↗
21. Denker, J.S., Gardner, W., Graf, H.P., Henderson, D., Howard, R., Hubbard, W., Jackel, L.D., Baird, H.S., and Guyon, I. (1989, January 27–30). Neural network recognizer for hand-written zip code digits. Proceedings of the Advances in Neural Information Processing Systems (NIPS 1989), Denver, CO, USA.
22. Coupled local–global adaptation for multi-source transfer learning10.1016/j.neucom.2017.06.051 ↗
23. Ganin, Y., and Lempitsky, V. (2015, January 7–9). Unsupervised Domain Adaptation by Backpropagation. Proceedings of the International Conference on Machine Learning, Lille, France.
24. Zhang, W., Ouyang, W., Li, W., and Xu, D. (2018, January 18–22). Collaborative and Adversarial Network for Unsupervised domain adaptation. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Salt Lake City, Utah.10.1109/CVPR.2018.00400 ↗
25. Tzeng, E., Hoffman, J., Darrell, T., and Saenko, K. (2015, January 7–13). Simultaneous deep transfer across domains and tasks. Proceedings of the 2015 IEEE International Conference onComputer Vision (ICCV), Santiago, Chile.10.1109/ICCV.2015.463 ↗
26. Tzeng, E., Hoffman, J., Saenko, K., and Darrell, T. (2017, January 21–26). Adversarial Discriminative Domain Adaptation. Proceedings of the 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Honolulu, HI, USA.10.1109/CVPR.2017.316 ↗
27. Isola, P., Zhu, J.Y., Zhou, T., and Efros, A.A. (2017, January 21–26). Image-to-Image Translation with Conditional Adversarial Networks. Proceedings of the 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Honolulu, HI, USA.10.1109/CVPR.2017.632 ↗
28. Zhu, J.Y., Park, T., Isola, P., and Efros, A.A. (2017, January 22–29). Unpaired Image-to-Image Translation Using Cycle-Consistent Adversarial Networks. Proceedings of the 2017 IEEE International Conference on Computer Vision (ICCV), Venice, Italy.10.1109/ICCV.2017.244 ↗
29. Semantic invariant cross-domain image generation with generative adversarial networks10.1016/j.neucom.2018.02.092 ↗
30. Bousmalis, K., Silberman, N., Dohan, D., Erhan, D., and Krishnan, D. (2017, January 21–26). Unsupervised Pixel-Level Domain Adaptation with Generative Adversarial Networks. Proceedings of the 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Honolulu, HI, USA.10.1109/CVPR.2017.18 ↗
31. Coupled generative adversarial stacked Auto-encoder: CoGASA10.1016/j.neunet.2018.01.002 ↗
32. Kingma, D.P., and Welling, M. (arXiv, 2013). Auto-encoding variational bayes, arXiv.
33. He, K., Zhang, X., Ren, S., and Sun, J. (2016, January 27–30). Deep residual learning for image recognition. Proceedings of the 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Las Vegas, NV, USA.10.1109/CVPR.2016.90 ↗
34. Larsen, A.B.L., Sønderby, S.K., Larochelle, H., and Winther, O. (2016, January 20–22). Autoencoding beyond pixels using a learned similarity metric. Proceedings of the International Conference on Machine Learning, New York, NY, USA.
35. Automatic classification of single facial images10.1109/34.817413 ↗
36. Lyons, M., Akamatsu, S., Kamachi, M., and Gyoba, J. (1998, January 14–16). Coding facial expressions with gabor wavelets. Proceedings of the 1998 IEEE International Conference on Automatic Face and Gesture Recognition, Nara, Japan.
37. Valstar, M., and Pantic, M. (2010, January 23). Induced disgust, happiness and surprise: An addition to the mmi facial expression database. Proceedings of the 3rd International Workshop on EMOTION (Satellite of LREC): Corpora for Research on Emotion and Affect, Valletta, Malta.
38. Pantic, M., Valstar, M., Rademaker, R., and Maat, L. (2005, January 6). Web-based database for facial expression analysis. Proceedings of the IEEE International Conference on Multimedia and Expo (ICME 2005), Amsterdam, The Netherlands.
39. Lucey, P., Cohn, J.F., Kanade, T., Saragih, J., Ambadar, Z., and Matthews, I. (2010, January 13–18). The extended cohn-kanade dataset (ck+): A complete dataset for action unit and emotion-specified expression. Proceedings of the 2010 IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops (CVPRW), San Francisco, CA, USA.10.1109/CVPRW.2010.5543262 ↗
40. Accelerating t-SNE using tree-based algorithms
41. Saenko, K., Kulis, B., Fritz, M., and Darrell, T. (2010). Adapting visual category models to new domains. European Conference on Computer Vision, Springer.10.1007/978-3-642-15561-1_16 ↗