research-article

Disentanglement then reconstruction: : Unsupervised domain adaptation by twice distribution alignments

Authors:

Xue LiAuthors Info & Claims

Volume 237, Issue PB

https://doi.org/10.1016/j.eswa.2023.121498

Published: 01 March 2024 Publication History

Abstract

Unsupervised domain adaptation aims to transfer knowledge from labeled source domain to unlabeled target domain. Traditional methods usually achieve domain adaptation by aligning the distributions between two domains once. We propose to align the distributions twice by a disentanglement and reconstruction process, named DTR (Disentanglement Then Reconstruction). Specifically, a feature extraction network shared by both source and target domains is used to obtain the original extracted features, then the domain invariant features and domain specific features are disentangled from the original extracted features. The domain distributions are explicitly aligned when disentangling domain invariant features. Based on the disentangled features, the class prototypes and domain prototypes can be estimated. Then, a reconstructor is trained by the disentangled features. By this reconstructor, we can construct prototypes in the original feature space using the corresponding class prototype and domain prototype similarly. The extracted features are forced to close the corresponding constructed prototypes. In this process, the distribution between two domains is implicitly aligned again. Experiment results on several public datasets confirm the effectiveness of our method.

Highlights

•

Our method can use domain invariant features and domain specific features very well.

•

By learning more compact features, domain distributions will be aligned again.

•

The experiments on public datasets are conducted and the proposed method works well.

•

Thorough analysis experiments also illustrates the advantages of our method.

References

[1]

An Y., Zhang K., Chai Y., Liu Q., Huang X., Domain adaptation network base on contrastive learning for bearings fault diagnosis under variable working conditions, Expert Systems with Applications 212 (2023).

Digital Library

[2]

Bendavid S., Blitzer J., Crammer K., Kulesza A., Pereira F., Vaughan J.W., A theory of learning from different domains, Machine Learning 79 (1) (2010) 151–175.

[3]

Cai, Q., Pan, Y., Ngo, C.-W., Tian, X., Duan, L., & Yao, T. (2019). Exploring object relation in mean teacher for cross-domain detection. In Proceedings of the IEEE/CVF conference on computer vision and pattern recognition (pp. 11457–11466).

[4]

Chen, X., Wang, S., Long, M., & Wang, J. (2019). Transferability vs. Discriminability: Batch Spectral Penalization for Adversarial Domain Adaptation. In International conference on machine learning (pp. 1081–1090).

[5]

Chen, C., Xie, W., Huang, W., Rong, Y., Ding, X., Huang, Y., et al. (2019). Progressive Feature Alignment for Unsupervised Domain Adaptation. In Proceedings of the IEEE conference on computer vision and pattern recognition (pp. 627–636).

[6]

Chen, M., Zhao, S., Liu, H., & Cai, D. (2020). Adversarial-learned loss for domain adaptation. In Proceedings of the AAAI conference on artificial intelligence, vol. 34, nol. 04 (pp. 3521–3528).

[7]

Dan J., Jin T., Chi H., Shen Y., Yu J., Zhou J., HOMDA: High-order moment-based domain alignment for unsupervised domain adaptation, Knowledge-Based Systems 261 (2023).

[8]

Deng J., Li W., Chen Y., Duan L., Unbiased mean teacher for cross domain object detection, 2020, arXiv preprint arXiv:2003.00707.

[9]

Du Y., Zhou Y., Xie Y., Zhou D., Shi J., Lei Y., Unsupervised domain adaptation via progressive positioning of target-class prototypes, Knowledge-Based Systems 273 (2023).

[10]

Duan L., Tsang I.W., Xu D., Domain transfer multiple kernel learning, IEEE Transactions on Pattern Analysis and Machine Intelligence 34 (3) (2012) 465–479.

[11]

French, G., Mackiewicz, M., & Fisher, M. (2018). Self-ensembling for visual domain adaptation. In International conference on learning representations, no. 6.

[12]

Fu S., Chen J., Lei L., Cooperative attention generative adversarial network for unsupervised domain adaptation, Knowledge-Based Systems 261 (2023).

[13]

Ganin Y., Ustinova E., Ajakan H., Germain P., Larochelle H., Laviolette F., et al., Domain-adversarial training of neural networks, Journal of Machine Learning Research 17 (1) (2016) 189–209.

[14]

Gong, B., Shi, Y., Sha, F., & Grauman, K. (2012). Geodesic flow kernel for unsupervised domain adaptation. In Proceedings of the IEEE conference on computer vision and pattern recognition (pp. 2066–2073).

[15]

Goodfellow I., Pougetabadie J., Mirza M., Xu B., Wardefarley D., Ozair S., et al., Generative adversarial nets, in: Advances in neural information processing systems, 2014, pp. 2672–2680.

[16]

He Z., Chen Y., Yuan S., Zhao J., Yuan Z., Polat K., et al., A novel unsupervised domain adaptation framework based on graph convolutional network and multi-level feature alignment for inter-subject ECG classification, Expert Systems with Applications 221 (2023).

[17]

He, K., Zhang, X., Ren, S., & Sun, J. (2016). Deep Residual Learning for Image Recognition. In Proceedings of the IEEE conference on computer vision and pattern recognition (pp. 770–778).

[18]

Kang, G., Jiang, L., Yang, Y., & Hauptmann, A. G. (2019). Contrastive adaptation network for unsupervised domain adaptation. In Proceedings of the IEEE/CVF conference on computer vision and pattern recognition (pp. 4893–4902).

[19]

Krishna K., Murty M.N., Genetic K-means algorithm, IEEE Transactions on Systems, Man and Cybernetics, Part B (Cybernetics) 29 (3) (1999) 433–439.

[20]

Kumar, A., Sattigeri, P., Wadhawan, K., Karlinsky, L., Feris, R. S., Freeman, B., et al. (2018). Co-regularized Alignment for Unsupervised Domain Adaptation. In NeurIPS.

[21]

Lee, C.-Y., Batra, T., Baig, M. H., & Ulbricht, D. (2019). Sliced wasserstein discrepancy for unsupervised domain adaptation. In Proceedings of the IEEE/CVF conference on computer vision and pattern recognition (pp. 10285–10295).

[22]

Li J., Jing M., Su H., Lu K., Zhu L., Shen H.T., Faster domain adaptation networks, IEEE Transactions on Knowledge and Data Engineering (2021).

[23]

Li J., Lü S., Li Z., Unsupervised domain adaptation via softmax-based prototype construction and adaptation, Information Sciences 609 (2022) 257–275.

[24]

Li, S., Lv, F., Xie, B., Liu, C. H., Liang, J., & Qin, C. (2021). Bi-Classifier Determinacy Maximization for Unsupervised Domain Adaptation. In Proceedings of the AAAI conference on artificial intelligence, vol. 35, no. 10 (pp. 8455–8464).

[25]

Li, S., Xie, M., Gong, K., Liu, C. H., Wang, Y., & Li, W. (2021). Transferable semantic augmentation for domain adaptation. In Proceedings of the IEEE/CVF conference on computer vision and pattern recognition (pp. 11516–11525).

[26]

Liang J., He R., Sun Z., Tan T., Aggregating randomized clustering-promoting invariant projections for domain adaptation, IEEE Transactions on Pattern Analysis and Machine Intelligence 41 (5) (2018) 1027–1042.

[27]

Liang J., He R., Sun Z., Tan T., Exploring uncertainty in pseudo-label guided unsupervised domain adaptation, Pattern Recognition 96 (2019).

[28]

Liang, J., Hu, D., & Feng, J. (2021). Domain adaptation with auxiliary target domain-oriented classifier. In Proceedings of the IEEE/CVF conference on computer vision and pattern recognition (pp. 16632–16642).

[29]

Liu P., Xiao T., Fan C., Zhao W., Tang X., Liu H., Importance-weighted conditional adversarial network for unsupervised domain adaptation, Expert Systems with Applications 155 (2020).

[30]

Long, M., Cao, Y., Wang, J., & Jordan, M. I. (2015). Learning Transferable Features with Deep Adaptation Networks. In International conference on machine learning (pp. 97–105).

[31]

Long M., Cao Z., Wang J., Jordan M.I., Conditional adversarial domain adaptation, in: Advances in neural information processing systems, 2018, pp. 1640–1650.

[32]

Long, M., Wang, J., Ding, G., Sun, J., & Yu, P. S. (2013). Transfer Feature Learning with Joint Distribution Adaptation. In Proceedings of the IEEE international conference on computer vision (pp. 2200–2207).

[33]

Long, M., Zhu, H., Wang, J., & Jordan, M. I. (2017). Deep transfer learning with joint adaptation networks. In International conference on machine learning (pp. 2208–2217).

[34]

Loshchilov I., Hutter F., Sgdr: Stochastic gradient descent with warm restarts, 2016, arXiv preprint arXiv:1608.03983.

[35]

Motiian, S., Piccirilli, M., Adjeroh, D., & Doretto, G. (2017). Unified Deep Supervised Domain Adaptation and Generalization. In Proceedings of the IEEE international conference on computer vision (pp. 5716–5726).

[36]

Pan S.J., Tsang I.W., Kwok J.T., Yang Q., Domain adaptation via transfer component analysis, IEEE Transactions on Neural Networks 22 (2) (2011) 199–210.

Digital Library

[37]

Pan S.J., Yang Q., A survey on transfer learning, IEEE Transactions on Knowledge and Data Engineering 22 (10) (2010) 1345–1359.

Digital Library

[38]

Peng, X., Huang, Z., Sun, X., & Saenko, K. (2019). Domain Agnostic Learning with Disentangled Representations. In International conference on machine learning (pp. 5102–5112).

[39]

Peng X., Usman B., Kaushik N., Hoffman J., Wang D., Saenko K., VisDA: The visual domain adaptation challenge, 2017, arXiv: Computer Vision and Pattern Recognition.

[40]

Pinheiro, P. O. (2018). Unsupervised Domain Adaptation with Similarity Learning. In Proceedings of the IEEE conference on computer vision and pattern recognition (pp. 8004–8013).

[41]

Russakovsky O., Deng J., Su H., Krause J., Satheesh S., Ma S., et al., ImageNet large scale visual recognition challenge, International Journal of Computer Vision 115 (3) (2015) 211–252.

Digital Library

[42]

Saenko, K., Kulis, B., Fritz, M., & Darrell, T. (2010). Adapting visual category models to new domains. In European conference on computer vision (pp. 213–226).

[43]

Saito, K., Kim, D., Sclaroff, S., Darrell, T., & Saenko, K. (2019). Semi-Supervised Domain Adaptation via Minimax Entropy. In Proceedings of the IEEE international conference on computer vision (pp. 8050–8058).

[44]

Saito, K., Kim, D., Teterwak, P., Sclaroff, S., Darrell, T., & Saenko, K. (2021). Tune it the right way: Unsupervised validation of domain adaptation via soft neighborhood density. In Proceedings of the IEEE/CVF international conference on computer vision (pp. 9184–9193).

[45]

Saito, K., Watanabe, K., Ushiku, Y., & Harada, T. (2018). Maximum Classifier Discrepancy for Unsupervised Domain Adaptation. In Proceedings of the IEEE conference on computer vision and pattern recognition (pp. 3723–3732).

[46]

Sankaranarayanan, S., Balaji, Y., Castillo, C. D., & Chellappa, R. (2018). Generate to Adapt: Aligning Domains Using Generative Adversarial Networks. In Proceedings of the IEEE conference on computer vision and pattern recognition (pp. 8503–8512).

[47]

Shu, R., Bui, H., Narui, H., & Ermon, S. (2018). A DIRT-T Approach to Unsupervised Domain Adaptation. In International conference on learning representations.

[48]

Sutskever I., Martens J., Dahl G., Hinton G., On the importance of initialization and momentum in deep learning, in: International conference on machine learning, PMLR, 2013, pp. 1139–1147.

[49]

Tarvainen, A., & Valpola, H. (2017). Mean teachers are better role models: Weight-averaged consistency targets improve semi-supervised deep learning results. In Proceedings of the 31st international conference on neural information processing systems (pp. 1195–1204).

[50]

Tian Q., Zhou J., Chu Y., Joint bi-adversarial learning for unsupervised domain adaptation, Knowledge-Based Systems 248 (2022).

[51]

Torralba, A., & Efros, A. A. (2011). Unbiased look at dataset bias. In Proceedings of the IEEE conference on computer vision and pattern recognition (pp. 1521–1528).

[52]

Tzeng, E., Hoffman, J., Darrell, T., & Saenko, K. (2015). Simultaneous Deep Transfer Across Domains and Tasks. In Proceedings of the IEEE international conference on computer vision (pp. 4068–4076).

[53]

Tzeng, E., Hoffman, J., Saenko, K., & Darrell, T. (2017). Adversarial Discriminative Domain Adaptation. In Proceedings of the IEEE conference on computer vision and pattern recognition (pp. 2962–2971).

[54]

Tzeng, E., Hoffman, J., Zhang, N., Saenko, K., & Darrell, T. (2014). Deep Domain Confusion: Maximizing for Domain Invariance. In Proceedings of the IEEE conference on computer vision and pattern recognition.

[55]

Venkateswara, H., Eusebio, J., Chakraborty, S., & Panchanathan, S. (2017). Deep hashing network for unsupervised domain adaptation. In Proceedings of the IEEE conference on computer vision and pattern recognition (pp. 5018–5027).

[56]

Wang Q., Meng F., Breckon T.P., Data augmentation with norm-AE and selective pseudo-labelling for unsupervised domain adaptation, Neural Networks 161 (2023) 614–625.

[57]

Wang X., Schneider J., Flexible transfer learning under support and model shift, in: Advances in neural information processing systems, 2014, pp. 1898–1906.

[58]

Wei G., Wei Z., Huang L., Nie J., Li X., Center-aligned domain adaptation network for image classification, Expert Systems with Applications 168 (2021).

[59]

Wei X., Wen B., Yang F., Liu Y., Zhao C., Hu D., et al., Task-oriented contrastive learning for unsupervised domain adaptation, Expert Systems with Applications 229 (2023).

[60]

Xia, H., & Ding, Z. (2020). Structure preserving generative cross-domain learning. In Proceedings of the IEEE/CVF conference on computer vision and pattern recognition (pp. 4364–4373).

[61]

Xie, S., Zheng, Z., Liang, C., & Chuan, C. (2018). Learning Semantic Representations for Unsupervised Domain Adaptation. In International conference on machine learning (pp. 5419–5428).

[62]

Xu, R., Li, G., Yang, J., & Lin, L. (2019). Larger Norm More Transferable: An Adaptive Feature Norm Approach for Unsupervised Domain Adaptation. In Proceedings of the IEEE international conference on computer vision (pp. 1426–1435).

[63]

Yang, G., Xia, H., Ding, M., & Ding, Z. (2020). Bi-directional generation for unsupervised domain adaptation. In Proceedings of the AAAI conference on artificial intelligence, vol. 34, no. 04 (pp. 6615–6622).

[64]

Zhang, W., Ouyang, W., Li, W., & Xu, D. (2018). Collaborative and Adversarial Network for Unsupervised Domain Adaptation. In Proceedings of the IEEE conference on computer vision and pattern recognition (pp. 3801–3809).

[65]

Zhang, K., Schlkopf, B., Muandet, K., & Wang, Z. (2013). Domain Adaptation under Target and Conditional Shift. In International conference on machine learning (pp. 819–827).

[66]

Zhang, Y., Tang, H., Jia, K., & Tan, M. (2019). Domain-symmetric networks for adversarial domain adaptation. In Proceedings of the IEEE/CVF conference on computer vision and pattern recognition (pp. 5031–5040).

[67]

Zhang C., Zhang J., Transferable regularization and normalization: Towards transferable feature learning for unsupervised domain adaptation, Information Sciences 609 (2022) 595–604.

[68]

Zhang C., Zhao Q., Deep discriminative domain adaptation, Information Sciences 575 (2021) 599–610.

[69]

Zhang C., Zhao Q., Wang Y., Hybrid adversarial network for unsupervised domain adaptation, Information Sciences 514 (2020) 44–55.

Digital Library

[70]

Zhang C., Zhao Q., Wang Y., Transferable attention networks for adversarial domain adaptation, Information Sciences 539 (2020) 422–433.

[71]

Zhou L., Xiao S., Ye M., Zhu X., Li S., Adaptive mutual learning for unsupervised domain adaptation, IEEE Transactions on Circuits and Systems for Video Technology (2023).

[72]

Zhou L., Ye M., Xiao S., Domain adaptation based on source category prototypes, Neural Computing and Applications 34 (23) (2022) 21191–21203.

[73]

Zhou L., Ye M., Zhang D., Zhu C., Ji L., Prototype-based multisource domain adaptation, IEEE Transactions on Neural Networks and Learning Systems (2021).

[74]

Zhou, L., Ye, M., Zhu, X., Li, S., & Liu, Y. (2022). Class Discriminative Adversarial Learning for Unsupervised Domain Adaptation. In Proceedings of the 30th ACM international conference on multimedia (pp. 4318–4326).

[75]

Zhu, J., Park, T., Isola, P., & Efros, A. A. (2017). Unpaired Image-to-Image Translation Using Cycle-Consistent Adversarial Networks. In Proceedings of the IEEE international conference on computer vision (pp. 2242–2251).

Cited By

Kataoka JYoon H(2024)AVATARExpert Systems with Applications: An International Journal10.1016/j.eswa.2024.125147258:COnline publication date: 15-Dec-2024
https://dl.acm.org/doi/10.1016/j.eswa.2024.125147
Wang SXiao QWang KYang XZhang X(2024)Mutual-weighted feature disentanglement for unsupervised domain adaptationMultimedia Systems10.1007/s00530-024-01477-830:6Online publication date: 7-Oct-2024
https://dl.acm.org/doi/10.1007/s00530-024-01477-8

Index Terms

Disentanglement then reconstruction: Unsupervised domain adaptation by twice distribution alignments
1. Computing methodologies
  1. Artificial intelligence
  2. Machine learning
    1. Learning paradigms
    2. Machine learning approaches

Index terms have been assigned to the content through auto-classification.

Recommendations

Mutual-weighted feature disentanglement for unsupervised domain adaptation: Mutual-weighted feature disentanglement for unsupervised...
Abstract
Unsupervised domain adaptation (UDA) aims to reduce the distribution discrepancy across domains, enabling the transfer of knowledge from the labeled source domain to the unlabeled target domain. The main focus of most current UDA methods lies on ...
Attention-Enhanced Disentangled Representation Learning for Unsupervised Domain Adaptation in Cardiac Segmentation
Medical Image Computing and Computer Assisted Intervention – MICCAI 2022
Abstract
To overcome the barriers of multimodality and scarcity of annotations in medical image segmentation, many unsupervised domain adaptation (UDA) methods have been proposed, especially in cardiac segmentation. However, these methods may not ...
Informative Class-Conditioned Feature Alignment for Unsupervised Domain Adaptation
MM '21: Proceedings of the 29th ACM International Conference on Multimedia

The goal of unsupervised domain adaptation is to learn a task classifier that performs well for the unlabeled target domain by borrowing rich knowledge from a well-labeled source domain. Although remarkable breakthroughs have been achieved in learning ...

Comments

Information & Contributors

Information

Published In

cover image Expert Systems with Applications: An International Journal

Expert Systems with Applications: An International Journal Volume 237, Issue PB

Mar 2024

1582 pages

Issue’s Table of Contents

Elsevier Ltd.

Publisher

Pergamon Press, Inc.

United States

Publication History

Published: 01 March 2024

Author Tags

Qualifiers

Research-article

Contributors

Other Metrics

View Article Metrics

Bibliometrics & Citations

Bibliometrics

Article Metrics

2
Total Citations
View Citations
0
Total Downloads

Downloads (Last 12 months)0
Downloads (Last 6 weeks)0

Reflects downloads up to 04 Feb 2025

Other Metrics

View Author Metrics

Citations

Cited By

Kataoka JYoon H(2024)AVATARExpert Systems with Applications: An International Journal10.1016/j.eswa.2024.125147258:COnline publication date: 15-Dec-2024
https://dl.acm.org/doi/10.1016/j.eswa.2024.125147
Wang SXiao QWang KYang XZhang X(2024)Mutual-weighted feature disentanglement for unsupervised domain adaptationMultimedia Systems10.1007/s00530-024-01477-830:6Online publication date: 7-Oct-2024
https://dl.acm.org/doi/10.1007/s00530-024-01477-8

View Options

View options

Figures

Tables

Media

View Issue’s Table of Contents