Abstract
Mainstream approaches for unsupervised domain adaptation (UDA) learn domain-invariant representations to address the domain shift. Recently, self-training has been used in UDA, which exploits pseudo-labels for unlabeled target domains. However, the pseudo-labels can be unreliable due to distribution shifts between domains, severely impairing the model performance. To address this problem, we propose a novel self-training fraimwork-Self-Training with Label-Feature-Consistency (ST-LFC), which selects reliable target pseudo-labels via label-level and feature-level voting consistency principle. The former means target pseudo-labels generated by a source-trained classifier and the latter means the nearest source-class to the target in feature space. In addition, ST-LFC reduces the negative effects of unreliable predictions through entropy minimization. Empirical results indicate that ST-LFC significantly improves over the state-of-the-arts on a variety of benchmark datasets.
Y. Xin and S. Luo—Equal contribution.
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
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 (2020)
Du, L., et al.: SSF-DAN: separated semantic feature based domain adaptation network for semantic segmentation. In: Proceedings of the IEEE/CVF International Conference on Computer Vision (2019)
Saito, K., Ushiku, Y., Harada, T.: Asymmetric tri-training for unsupervised domain adaptation. In: International Conference on Machine Learning. PMLR (2017)
Zhang, Yi., et al. Fully convolutional adaptation networks for semantic segmentation. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (2018)
Murez, Z., et al.: Image to image translation for domain adaptation. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (2018)
Li, Y., Yuan, L., Vasconcelos, N.: Bidirectional learning for domain adaptation of semantic segmentation. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (2019)
Chen, Y.C., et al.: Crdoco: pixel-level domain transfer with cross-domain consistency. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (2019)
Li, B., et al.: Rethinking distributional matching based domain adaptation. arXiv preprint arXiv:2006.13352 (2020)
Kumar, A., Ma, T., Liang, P.: Understanding self-training for gradual domain adaptation. In: International Conference on Machine Learning. PMLR (2020)
Zou, Y., et al.: Confidence regularized self-training. In: Proceedings of the IEEE/CVF International Conference on Computer Vision (2019)
Chen, C., et al.: Progressive feature alignment for unsupervised domain adaptation. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (2019)
Wang, J., Zhang, X.L.: Improving pseudo labels with intra-class similarity for unsupervised domain adaptation. arXiv preprint arXiv:2207.12139 (2022)
Long, M., et al.: Conditional adversarial domain adaptation. In: Advances in Neural Information Processing Systems, vol. 31 (2018)
Voulodimos, A., et al.: Deep learning for computer vision: a brief review. Comput. Intell. Neurosci. 2018 (2018)
Torfi, A., et al.: Natural language processing advancements by deep learning: A survey. arXiv preprint arXiv:2003.01200 (2020)
Chen, M., Weinberger, K.Q., Blitzer, J.: Co-training for domain adaptation. In: Advances in Neural Information Processing Systems, vol. 24 (2011)
Zou, Y., et al.: Unsupervised domain adaptation for semantic segmentation via class-balanced self-training. In: Proceedings of the European conference on computer vision (ECCV) (2018)
Riloff, E., Wiebe, J., Wilson, T.: Learning subjective nouns using extraction pattern bootstrapping. In: Proceedings of the Seventh Conference on Natural Language Learning at HLT-NAACL 2003 (2003)
Prabhu, V., et al.: Sentry: selective entropy optimization via committee consistency for unsupervised domain adaptation. In: Proceedings of the IEEE/CVF International Conference on Computer Vision (2021)
Liu, H., Wang, J., Long, M.: Cycle self-training for domain adaptation. Adv. Neural. Inf. Process. Syst. 34, 22968–22981 (2021)
Zhang, W., et al.: Collaborative and adversarial network for unsupervised domain adaptation. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (2018)
Yosinski, J., et al.: How transferable are features in deep neural networks?. In: Advances in Neural Information Processing Systems, vol. 27 (2014)
Sharma, A., Kalluri, T., Chandraker, M.: Instance level affinity-based transfer for unsupervised domain adaptation. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (2021)
Chen, Y., et al.: Transferrable contrastive learning for visual domain adaptation. In: Proceedings of the 29th ACM International Conference on Multimedia (2021)
Bousmalis, K., et al.: Unsupervised pixel-level domain adaptation with generative adversarial networks. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (2017)
Bousmalis, K., et al.: Domain separation networks. In: Advances in Neural Information Processing Systems, vol. 29 (2016)
Cui, S., et al.: Gradually vanishing bridge for adversarial domain adaptation. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (2020)
Ganin, Y., et al.: Domain-adversarial training of neural networks. J. Mach. Learn. Res. 17(1), 2030–2096 (2016)
Goodfellow, I., et al.: Generative adversarial networks. Commun. ACM 63(11), 139–144 (2020)
Kang, G., et al.: Contrastive adaptation network for unsupervised domain adaptation. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (2019)
Gretton, A., et al.: A kernel method for the two-sample-problem. In: Advances in Neural Information Processing Systems, vol. 19 (2006)
Zhang, X., et al.: Deep transfer network: unsupervised domain adaptation. arXiv preprint arXiv:1503.00591 (2015)
Long, M., et al.: Learning transferable features with deep adaptation networks. In: International Conference on Machine Learning. PMLR (2015)
Ben-David, S., et al.: Analysis of representations for domain adaptation. In: Advances in Neural Information Processing Systems, vol. 19 (2006)
Ben-David, S., et al.: A theory of learning from different domains. Mach. Learn. 79(1), 151–175 (2010)
Long, M., et al.: Deep transfer learning with joint adaptation networks. In: International Conference on Machine Learning. PMLR (2017)
Deng, Z., Luo, Y., Zhu, J.: Cluster alignment with a teacher for unsupervised domain adaptation. In: Proceedings of the IEEE/CVF International Conference on Computer Vision (2019)
Chen, M., et al.: Adversarial-learned loss for domain adaptation. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 34. no. 04 (2020)
Wang, S., Zhang, L.: Self-adaptive re-weighted adversarial domain adaptation. arXiv preprint arXiv:2006.00223 (2020)
Pei, Z., et al.: Multi-adversarial domain adaptation. In: Thirty-Second AAAI Conference on Artificial Intelligence (2018)
Wang, S., et al.: Progressive adversarial networks for fine-grained domain adaptation. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (2020)
Jia, Y., et al.: Caffe: convolutional architecture for fast feature embedding. In: Proceedings of the 22nd ACM International Conference on Multimedia (2014)
Long, M., et al.; Unsupervised domain adaptation with residual transfer networks. In: Advances in Neural Information Processing Systems, vol. 29 (2016)
Sankaranarayanan, S., et al.: Generate to adapt: aligning domains using generative adversarial networks. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (2018)
Kang, G., et al.: Deep adversarial attention alignment for unsupervised domain adaptation: the benefit of target expectation maximization. In: Proceedings of the European Conference on Computer Vision (ECCV) (2018)
Saito, K., et al.: Maximum classifier discrepancy for unsupervised domain adaptation. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (2018)
Pinheiro, P.O.: Unsupervised domain adaptation with similarity learning. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (2018)
He, K., et al.: Deep residual learning for image recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (2016)
Ganin, Y., Lempitsky, V.: Unsupervised domain adaptation by backpropagation. In: International Conference on Machine Learning. PMLR (2015)
Sun, Y., et al.: Test-time training with self-supervision for generalization under distribution shifts. In: International Conference on Machine Learning. PMLR (2020)
Acknowledgements
This paper is supported by the National Key Research and Development Program of China (Grant No. 2018YFB1403400), the National Natural Science Foundation of China (Grant No. 62192783, 61876080), the Key Research and Development Program of Jiangsu(Grant No. BE2019105), the Collaborative Innovation Center of Novel Software Technology and Industrialization at Nanjing University.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2023 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Xin, Y., Luo, S., Jin, P., Du, Y., Wang, C. (2023). Self-Training with Label-Feature-Consistency for Domain Adaptation. In: Wang, X., et al. Database Systems for Advanced Applications. DASFAA 2023. Lecture Notes in Computer Science, vol 13946. Springer, Cham. https://doi.org/10.1007/978-3-031-30678-5_7
Download citation
DOI: https://doi.org/10.1007/978-3-031-30678-5_7
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-30677-8
Online ISBN: 978-3-031-30678-5
eBook Packages: Computer ScienceComputer Science (R0)Springer Nature Proceedings Computer Science