Abstract
Unsupervised domain adaptation aims to transfer knowledge from a labeled source domain to an unlabeled target domain. Although having achieved remarkable progress, most existing methods only focus on learning domain-invariant features and achieving a small source error. They ignore the discrepancy between labeling functions which will also cause discrepancy across domains. Inspired by this observation, we propose a novel method to simultaneously perform feature adaptation and labeling function adaptation. Specifically, for the feature adaptation, a domain discriminator is trained to reduce the discrepancy between feature distributions across domains. For the labeling function adaptation, we introduce a target predictor and a predictor discriminator. The target predictor is trained on target samples with pseudo-labels. The predictor discriminator is a novel component and is trained to distinguish whether the prediction output is from the source or the target predictor while the feature extractor and the label predictors try to confuse the predictor discriminator in an adversarial manner. Additionally, the intrinsic characteristics of the target domain are expected to be exploited thanks to the task-specific training. Comprehensive experiments are conducted and results validate the effectiveness of labeling function adaptation and demonstrate that our approach outperforms state-of-the-art methods.
F. Cui and Y. Chen—The first two authors contributed equally.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Acuna, D., Zhang, G., Law, M.T., Fidler, S.: f-domain-adversarial learning: theory and algorithms. In: ICML (2021)
Ben-David, S., Blitzer, J., Crammer, K., Kulesza, A., Pereira, F.C., Vaughan, J.W.: A theory of learning from different domains. Mach. Learn. 79, 151–175 (2009)
Cicek, S., Soatto, S.: Unsupervised domain adaptation via regularized conditional alignment. In: 2019 IEEE/CVF International Conference on Computer Vision (ICCV), pp. 1416–1425 (2019)
Du, Y., Chen, Y., Cui, F., Zhang, X., Wang, C.J.: Cross-domain error minimization for unsupervised domain adaptation. In: DASFAA (2021)
Du, Y., Tan, Z., Chen, Q., Zhang, X., Yao, Y., Wang, C.J.: Dual adversarial domain adaptation. ArXiv abs/2001.00153 (2020)
Du, Y., Yang, H., Chen, M., Jiang, J., Luo, H., Wang, C.J.: Generation, augmentation, and alignment: a pseudo-source domain based method for source-free domain adaptation. ArXiv abs/2109.04015 (2021)
Fu, B., Cao, Z., Wang, J., Long, M.: Transferable query selection for active domain adaptation. In: CVPR, pp. 7268–7277 (2021)
Ganin, Y., Lempitsky, V.: Unsupervised domain adaptation by backpropagation. In: ICML (2015)
Ganin, Y., et al.: Domain-adversarial training of neural networks. J. Mach. Learn. Res. 17, 59:1–59:35 (2016)
Ghifary, M., Kleijn, W., Zhang, M., Balduzzi, D., Li, W.: Deep reconstruction-classification networks for unsupervised domain adaptation. In: ECCV (2016)
Goodfellow, I.J., et al.: Generative adversarial nets. In: NIPS (2014)
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 (2016)
Kumar, A., et al.: Co-regularized alignment for unsupervised domain adaptation. In: NeurIPS (2018)
Li, M., Ming Zhai, Y., Luo, Y.W., Ge, P., Ren, C.X.: Enhanced transport distance for unsupervised domain adaptation. In: CVPR (2020)
Liang, J., Hu, D., Feng, J.: Do we really need to access the source data? Source hypothesis transfer for unsupervised domain adaptation. In: ICML (2020)
Liu, H., Long, M., Wang, J., Jordan, M.I.: Transferable adversarial training: a general approach to adapting deep classifiers. In: ICML (2019)
Liu, X., et al.: Adversarial unsupervised domain adaptation with conditional and label shift: infer, align and iterate. In: ICCV (2021)
Long, M., Cao, Y., Wang, J., Jordan, M.I.: Learning transferable features with deep adaptation networks. In: ICML (2015)
Long, M., Cao, Z., Wang, J., Jordan, M.I.: Conditional adversarial domain adaptation. In: NeurIPS (2018)
Long, M., Wang, J., Ding, G., Sun, J., Yu, P.: Transfer feature learning with joint distribution adaptation. In: 2013 IEEE International Conference on Computer Vision, pp. 2200–2207 (2013)
Long, M., Zhu, H., Wang, J., Jordan, M.I.: Deep transfer learning with joint adaptation networks. ArXiv abs/1605.06636 (2017)
Luo, Y., Zhu, J., Li, M., Ren, Y., Zhang, B.: Smooth neighbors on teacher graphs for semi-supervised learning. In: CVPR, pp. 8896–8905 (2018)
Mansour, Y., Mohri, M., Rostamizadeh, A.: Domain adaptation: learning bounds and algorithms. In: COLT (2009)
Pan, S., Yang, Q.: A survey on transfer learning. IEEE Trans. Knowl. Data Eng. 22, 1345–1359 (2010)
Russakovsky, O., et al.: Imagenet large scale visual recognition challenge. Int. J. Comput. Vision 115, 211–252 (2015)
Saenko, K., Kulis, B., Fritz, M., Darrell, T.: Adapting visual category models to new domains. In: ECCV (2010)
Saito, K., Ushiku, Y., Harada, T.: Asymmetric tri-training for unsupervised domain adaptation. In: ICML (2017)
Saito, K., Watanabe, K., Ushiku, Y., Harada, T.: Maximum classifier discrepancy for unsupervised domain adaptation. In: CVPR, pp. 3723–3732 (2018)
Sankaranarayanan, S., Balaji, Y., Castillo, C.D., Chellappa, R.: Generate to adapt: aligning domains using generative adversarial networks. In: CVPR, pp. 8503–8512 (2018)
Shu, R., Bui, H.H., Narui, H., Ermon, S.: A DIRT-T approach to unsupervised domain adaptation. In: ICLR (2018)
Tzeng, E., Hoffman, J., Saenko, K., Darrell, T.: Adversarial discriminative domain adaptation. In: CVPR, pp. 2962–2971 (2017)
Venkateswara, H., Eusebio, J., Chakraborty, S., Panchanathan, S.: Deep hashing network for unsupervised domain adaptation. In: CVPR, pp. 5385–5394 (2017)
Wang, J., Feng, W., Chen, Y., Yu, H., Huang, M., Yu, P.S.: Visual domain adaptation with manifold embedded distribution alignment. In: MM 2018 (2018)
Wang, M., Deng, W.: Deep visual domain adaptation: a survey. Neurocomputing 312, 135–153 (2018)
Xu, X., Zhou, X., Venkatesan, R., Swaminathan, G., Majumder, O.: d-SNE: domain adaptation using stochastic neighborhood embedding. In: CVPR, pp. 2492–2501 (2019)
Yang, J., Zou, H., Zhou, Y., Zeng, Z., Xie, L.: Mind the discriminability: asymmetric adversarial domain adaptation. In: ECCV (2020)
Yu, C., Wang, J., Chen, Y., Huang, M.: Transfer learning with dynamic adversarial adaptation network. In: 2019 IEEE International Conference on Data Mining (ICDM), pp. 778–786 (2019)
Zhang, Y., Tang, H., Jia, K., Tan, M.: Domain-symmetric networks for adversarial domain adaptation. In: CVPR, pp. 5026–5035 (2019)
Zhang, Y., Liu, T., Long, M., Jordan, M.I.: Bridging theory and algorithm for domain adaptation. In: ICML (2019)
Zhao, H., des Combes, R.T., Zhang, K., Gordon, G.J.: On learning invariant representation for domain adaptation. In: ICML (2019)
Acknowledgement
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. 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
© 2022 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Cui, F., Chen, Y., Du, Y., Cao, Y., Wang, C. (2022). Joint Feature and Labeling Function Adaptation for Unsupervised Domain Adaptation. In: Gama, J., Li, T., Yu, Y., Chen, E., Zheng, Y., Teng, F. (eds) Advances in Knowledge Discovery and Data Mining. PAKDD 2022. Lecture Notes in Computer Science(), vol 13280. Springer, Cham. https://doi.org/10.1007/978-3-031-05933-9_34
Download citation
DOI: https://doi.org/10.1007/978-3-031-05933-9_34
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-05932-2
Online ISBN: 978-3-031-05933-9
eBook Packages: Computer ScienceComputer Science (R0)