Abstract
Image classification is an active research in the field of computer vision. There are still significant challenges in the classification accuracy of cross-domain images due to the privacy, human, and material cost issues involved in labeled data collection, and the distribution differences among the collected images of the same category. To address the above problems, unsupervised domain adaptation (UDA) methods emerge, which transfer prior knowledge from the labeled source domain to the unlabeled target domain. In this work, we propose a new UDA architecture, SADD, which performs feature-level and pixel-level discrimination in a self-attention generative adversarial network. Specifically, we use the self-attention mechanism in extracting features to obtain globally dependent embeddings. In addition, we apply pixel-level distribution consistency loss on the embedding-generated images to mitigate the pixel-level distribution shifts due to unstable image style shifts. Further, we use discriminators for embedding reconstruction to assist the feature extractor in aligning features and enhancing the classification ability of the classifier. We evaluate our approach on the DIGITS classification dataset and the OFFICE-31 recognition dataset, and the results demonstrate the robustness and superiority of our approach.
Supported by Natural Science Foundation of Sichuan Province under Grant 2022NSFSC0552, and National Natural Science Foundation of China (62006165).
Z. Dai and J. Yang—Authors contribute equally to this work.
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
Krizhevsky, A., Sutskever, I., Hinton, G.E.: ImageNet classification with deep convolutional neural networks. Commun. ACM 60, 84–90 (2012)
Simonyan, K., Zisserman, A.: Very Deep Convolutional Networks for Large-Scale Image Recognition. CoRR, abs/1409.1556 (2014)
Szegedy, C., Ioffe, S., Vanhoucke, V., Alemi, A.A.: Inception-V4, Inception-ResNet and the Impact of Residual Connections on Learning. arXiv, abs/1602.07261 (2016)
He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 770–778 (2015)
Li, Y., Lin, C., Li, H., et al.: Unsupervised domain adaptation with self-attention for post-disaster building damage detection. Neurocomputing 415, 27–39 (2020)
Sankaranarayanan, S., Balaji, Y., Castillo, C.D., et al.: Generate to adapt: aligning domains using generative adversarial networks. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 8503–8512 (2018)
Long, M., Zhu, H., Wang, J., et al.: Deep transfer learning with joint adaptation networks. In: International Conference on Machine Learning, pp. 2208–2217. PMLR (2017)
Shen, J., Qu, Y., Zhang, W., et al.: Wasserstein distance guided representation learning for domain adaptation. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 32, no. 1 (2018)
Tzeng, E., Hoffman, J., Zhang, N., et al.: Deep domain confusion: maximizing for domain invariance. arXiv preprint arXiv:1412.3474 (2014)
Long, M., Cao, Y., Wang, J., et al.: Learning transferable features with deep adaptation networks. In: International Conference on Machine Learning, pp. 97–105. PMLR (2015)
Sun, B., Saenko, K.: Deep CORAL: correlation alignment for deep domain adaptation. In: Hua, G., Jégou, H. (eds.) ECCV 2016. LNCS, vol. 9915, pp. 443–450. Springer, Cham (2016). https://doi.org/10.1007/978-3-319-49409-8_35
Chen, P., Zhao, R., He, T., Wei, K., Qidong, Y.: Unsupervised domain adaptation of bearing fault diagnosis based on join sliced Wasserstein distance. ISA Trans. 129, 504–519 (2022)
Nguyen, A., Tran, T., Gal, Y., Torr, P.H., Baydin, A.G.: KL Guided Domain Adaptation. arXiv, abs/2106.07780 (2021)
Ganin, Y., Ustinova, E., Ajakan, H., et al.: Domain-adversarial training of neural networks. J. Mach. Learn. Res. 17(1), 2096-2030 (2016)
Tzeng, E., Hoffman, J., Saenko, K., et al.: Adversarial discriminative domain adaptation. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 7167–7176 2017
Lee, J., Hwang, K., Kwak, M., et al.: Domain adaptation training of a transformer. In: 2022 IEEE International Conference on Consumer Electronics-Asia (ICCE-Asia), pp. 1–5. IEEE (2022)
Zhang, J., Huang, J., Tian, Z., et al.: Spectral unsupervised domain adaptation for visual recognition. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 9829–9840 (2022)
Ghifary, M., Kleijn, W.B., Zhang, M., Balduzzi, D., Li, W.: Deep reconstruction-classification networks for unsupervised domain adaptation. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016. LNCS, vol. 9908, pp. 597–613. Springer, Cham (2016). https://doi.org/10.1007/978-3-319-46493-0_36
Saito, K., Watanabe, K., Ushiku, Y., et al.: Maximum classifier discrepancy for unsupervised domain adaptation. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 3723–3732 (2018)
Bousmalis, K., Silberman, N., Dohan, D., et al.: Unsupervised pixel-level domain adaptation with generative adversarial networks. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 3722–3731 (2017)
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: 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 2667–2676 (2018)
Hoffman, J., et al.: CyCADA: cycle-consistent adversarial domain adaptation. In: International Conference on Machine Learning (2017)
Zhu, H., Yin, H., Xia, D., Wang, D., Liu, X., Zhu, S.: Joint pixel-level and feature-level unsupervised domain adaptation for surveillance face recognition. In: Chinese Conference on Pattern Recognition and Computer Vision (2022)
Chen, Z., Zhao, L., He, Q., Kuang, G.: Pixel-level and feature-level domain adaptation for heterogeneous SAR target recognition. IEEE Geosci. Remote Sens. Lett. 19, 1–5 (2022)
Poojary, A., Phapale, A., Salpekar, R., Balpande, S.: Self-Attention Generative Adversarial Network: The Latest Advancement in GAN (2020)
Odena, A., Olah, C., Shlens, J.: Conditional Image Synthesis with Auxiliary Classifier GANs. Presented at the (2016)
Liu, Z., et al.: Swin transformer: hierarchical vision transformer using shifted windows. In: 2021 IEEE/CVF International Conference on Computer Vision (ICCV), pp. 9992–10002 (2021)
Kingma, D.P., Ba, J.: Adam: a method for stochastic optimization. arXiv preprint arXiv:1412.6980 (2014)
Wang, G.G., Guo, T., Yu, Y., Su, H.: Unsupervised domain adaptation classification model based on generative adversarial network. Acta Electonica Sinica 48(6), 1190 (2020)
Poobathy, D., Chezian, R.M.: Edge detection operators: peak signal to noise ratio based comparison. Int. J. Image Graph. Sig. Process. 6, 55–61 (2014)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2024 The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.
About this paper
Cite this paper
Dai, Z., Yang, J., Fan, A., Jia, J., Chen, J. (2024). SADD: Generative Adversarial Networks via Self-attention and Dual Discriminator in Unsupervised Domain Adaptation. In: Liu, Q., et al. Pattern Recognition and Computer Vision. PRCV 2023. Lecture Notes in Computer Science, vol 14432. Springer, Singapore. https://doi.org/10.1007/978-981-99-8543-2_38
Download citation
DOI: https://doi.org/10.1007/978-981-99-8543-2_38
Published:
Publisher Name: Springer, Singapore
Print ISBN: 978-981-99-8542-5
Online ISBN: 978-981-99-8543-2
eBook Packages: Computer ScienceComputer Science (R0)