Abstract
Domain adaptation (DA) aims to transfer knowledge learned from a labeled source domain to an unlabeled or a less labeled but related target domain. Ideally, the source and target distributions should be aligned to each other equally to achieve unbiased knowledge transfer. However, due to the significant imbalance between the amount of annotated data in the source and target domains, usually only the target distribution is aligned to the source domain, leading to adapting unnecessary source specific knowledge to the target domain, i.e., biased domain adaptation. To resolve this problem, in this work, we delve into the transferability estimation problem in domain adaptation and propose a non-intrusive Unbiased Transferability Estimation Plug-in (UTEP) by modeling the uncertainty of a discriminator in adversarial-based DA methods to optimize unbiased transfer. We theoretically analyze the effectiveness of the proposed approach to unbiased transferability learning in DA. Furthermore, to alleviate the impact of imbalanced annotated data, we utilize the estimated uncertainty for pseudo label selection of unlabeled samples in the target domain, which helps achieve better marginal and conditional distribution alignments between domains. Extensive experimental results on a high variety of DA benchmark datasets show that the proposed approach can be readily incorporated into various adversarial-based DA methods, achieving state-of-the-art performance.
J. Hu and H. Zhong: Equal contribution.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Arjovsky, M., Bottou, L., Gulrajani, I., Lopez-Paz, D.: Invariant risk minimization. arXiv preprint arXiv:1907.02893 (2019)
Ben-David, S., Blitzer, J., Crammer, K., Kulesza, A., Pereira, F., Vaughan, J.W.: A theory of learning from different domains. Mach. Learn. 79, 151–175 (2010)
Ben-David, S., Blitzer, J., Crammer, K., Pereira, F.: Analysis of representations for domain adaptation. Adv. Neural Inf. Process. Syst. 19, 1–8 (2006)
Berthelot, D., Carlini, N., Goodfellow, I., Papernot, N., Oliver, A., Raffel, C.A.: Mixmatch: a holistic approach to semi-supervised learning. Adv. Neural Inf. Process. Syst. 32, 1–11 (2019)
Bickel, S., Scheffer, T.: Dirichlet-enhanced spam filtering based on biased samples. In: NIPS (2007)
Blundell, C., Cornebise, J., Kavukcuoglu, K., Wierstra, D.: Weight uncertainty in neural network. In: ICML (2015)
Chen, C., et al.: Progressive feature alignment for unsupervised domain adaptation. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 627–636 (2019)
Chen, X., Wang, S., Long, M., Wang, J.: Transferability vs. discriminability: batch spectral penalization for adversarial domain adaptation. In: International Conference on Machine Learning, pp. 1081–1090. PMLR (2019)
Cortes, C., Mansour, Y., Mohri, M.: Learning bounds for importance weighting. In: NIPS (2010)
Courty, N., Flamary, R., Tuia, D., Rakotomamonjy, A.: Optimal transport for domain adaptation. IEEE Trans. Pattern Anal. Mach. Intell. 39(9), 1853–1865 (2016)
Cui, S., Wang, S., Zhuo, J., Li, L., Huang, Q., Tian, Q.: Towards discriminability and diversity: Batch nuclear-norm maximization under label insufficient situations. In: CVPR (2020)
Der Kiureghian, A., Ditlevsen, O.: Aleatory or epistemic? Does it matter? Struct. Saf. 31(2), 105–112 (2009)
Donahue, J., et al.: DeCAF: a deep convolutional activation feature for generic visual recognition. In: International Conference on Machine Learning, pp. 647–655. PMLR (2014)
French, G., Mackiewicz, M., Fisher, M.: Self-ensembling for visual domain adaptation. In: International Conference on Learning Representations (ICLR) (2018)
Gal, Y., Ghahramani, Z.: Dropout as a Bayesian approximation: representing model uncertainty in deep learning. In: ICML (2016)
Ganin, Y., et al.: Domain-adversarial training of neural networks. J. Mach. Learn. Res. 17, 2096–3000 (2016)
Grandvalet, Y., Bengio, Y., et al.: Semi-supervised learning by entropy minimization. CAP 367, 281–296 (2005)
Guan, D., Huang, J., Xiao, A., Lu, S., Cao, Y.: Uncertainty-aware unsupervised domain adaptation in object detection. IEEE Trans. Multimed. 24, 2502–2514 (2021)
Han, Z., Sun, H., Yin, Y.: Learning transferable parameters for unsupervised domain adaptation. arXiv preprint arXiv:2108.06129 (2021)
He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: CVPR (2016)
Hoffman, J., et al.: CyCADA: cycle-consistent adversarial domain adaptation. In: International Conference on Machine Learning, pp. 1989–1998. PMLR (2018)
Hou, Y., Zheng, L.: Visualizing adapted knowledge in domain transfer. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 13824–13833, June 2021
Hu, J., Tuo, H., Wang, C., Qiao, L., Zhong, H., Jing, Z.: Multi-weight partial domain adaptation. In: BMVC (2019)
Hu, J., et al.: Discriminative partial domain adversarial network. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12372, pp. 632–648. Springer, Cham (2020). https://doi.org/10.1007/978-3-030-58583-9_38
Hu, J., Tuo, H., Wang, C., Zhong, H., Pan, H., Jing, Z.: Unsupervised satellite image classification based on partial transfer learning. Aerosp. Syst. 3(1), 21–28 (2019). https://doi.org/10.1007/s42401-019-00038-6
Hu, J., et al.: Self-adaptive partial domain adaptation. arXiv preprint arXiv:2109.08829 (2021)
Hu, L., Kan, M., Shan, S., Chen, X.: Unsupervised domain adaptation with hierarchical gradient synchronization. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 4043–4052 (2020)
Iandola, F.N., Han, S., Moskewicz, M.W., Ashraf, K., Dally, W.J., Keutzer, K.: SqueezeNet: alexnet-level accuracy with 50\(\times \) fewer parameters and\(<\)0.5 mb model size. arXiv preprint arXiv:1602.07360 (2016)
Jiang, J., Baixu, C., Bo, F., Mingsheng, L.: Transfer-learning-library. GitHub (2020)
Jin, Y., Wang, X., Long, M., Wang, J.: Minimum class confusion for versatile domain adaptation. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) .: Minimum class confusion for versatile domain adaptation. LNCS, vol. 12366, pp. 464–480. Springer, Cham (2020). https://doi.org/10.1007/978-3-030-58589-1_28
Kang, G., Jiang, L., Yang, Y., Hauptmann, A.G.: Contrastive adaptation network for unsupervised domain adaptation. In: CVPR, pp. 4893–4902 (2019)
Kendall, A., Gal, Y.: What uncertainties do we need in Bayesian deep learning for computer vision? arXiv preprint arXiv:1703.04977 (2017)
Kurmi, V.K., Kumar, S., Namboodiri, V.P.: Attending to discriminative certainty for domain adaptation. In: CVPR, pp. 491–500 (2019)
Li, B., Wang, Y., Zhang, S., Li, D., Keutzer, K., Darrell, T., Zhao, H.: Learning invariant representations and risks for semi-supervised domain adaptation. In: CVPR (2021)
Li, G., Kang, G., Zhu, Y., Wei, Y., Yang, Y.: Domain consensus clustering for universal domain adaptation. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 9757–9766 (June 2021)
Li, J., Chen, E., Ding, Z., Zhu, L., Shen, H.T.: Maximum density divergence for domain adaptation. IEEE Trans. Pattern Anal. Mach. Intell. 43, 3918–3930 (2020)
Liang, J., He, R., Sun, Z., Tan, T.: Exploring uncertainty in pseudo-label guided unsupervised domain adaptation. Pattern Recogn. 96, 106996 (2019)
Liu, H., Wang, J., Long, M.: Cycle self-training for domain adaptation. arXiv preprint arXiv:2103.03571 (2021)
Long, M., Cao, Z., Wang, J., Jordan, M.I.: Conditional adversarial domain adaptation. In: NeurIPS (2018)
Long, M., Cao, Y., Wang, J., Jordan, M.: Learning transferable features with deep adaptation networks. In: ICML (2015)
Long, M., Zhu, H., Wang, J., Jordan, M.I.: Unsupervised domain adaptation with residual transfer networks. arXiv preprint arXiv:1602.04433 (2016)
Louizos, C., Welling, M.: Multiplicative normalizing flows for variational bayesian neural networks. In: ICML (2017)
Luo, Y.W., Ren, C.X.: Conditional bures metric for domain adaptation. In: CVPR (2021)
Luo, Z., Zou, Y., Hoffman, J., Fei-Fei, L.: Label efficient learning of transferable representations across domains and tasks. arXiv preprint arXiv:1712.00123 (2017)
Pan, Y., Yao, T., Li, Y., Wang, Y., Ngo, C.W., Mei, T.: Transferrable prototypical networks for unsupervised domain adaptation. In: CVPR (2019)
Park, S., Bastani, O., Weimer, J., Lee, I.: Calibrated prediction with covariate shift via unsupervised domain adaptation. In: AISTATS (2020)
Parmar, N., et al.: Image transformer. In: International Conference on Machine Learning, pp. 4055–4064. PMLR (2018)
Pawlowski, N., Brock, A., Lee, M.C.H., Rajchl, M., Glocker, B.: Implicit weight uncertainty in neural networks. arXiv preprint arXiv:1711.01297 (2017)
Qin, J.: Inferences for case-control and semiparametric two-sample density ratio models. Biometrika 85(3), 619–630 (1998)
Rizve, M.N., Duarte, K., Rawat, Y.S., Shah, M.: In defense of pseudo-labeling: an uncertainty-aware pseudo-label selection framework for semi-supervised learning. In: ICLR (2020)
Saenko, K., Kulis, B., Fritz, M., Darrell, T.: Adapting visual category models to new domains. In: Daniilidis, K., Maragos, P., Paragios, N. (eds.) ECCV 2010. LNCS, vol. 6314, pp. 213–226. Springer, Heidelberg (2010). https://doi.org/10.1007/978-3-642-15561-1_16
Saito, K., Kim, D., Sclaroff, S., Darrell, T., Saenko, K.: Semi-supervised domain adaptation via minimax entropy. In: ICCV (2019)
Tang, H., Chen, K., Jia, K.: Unsupervised domain adaptation via structurally regularized deep clustering. In: CVPR, pp. 8725–8735 (2020)
Tzeng, E., Hoffman, J., Saenko, K., Darrell, T.: Adversarial discriminative domain adaptation. In: CVPR (2017)
Wang, X., Li, L., Ye, W., Long, M., Wang, J.: Transferable attention for domain adaptation. In: AAAI (2019)
Wang, X., Long, M., Wang, J., Jordan, M.: Transferable calibration with lower bias and variance in domain adaptation. Adv. Neural Inf. Process. Syst. 33, 19212–19223 (2020)
Wen, J., Zheng, N., Yuan, J., Gong, Z., Chen, C.: Bayesian uncertainty matching for unsupervised domain adaptation. arXiv preprint arXiv:1906.09693 (2019)
Xiao, N., Zhang, L.: Dynamic weighted learning for unsupervised domain adaptation. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 15242–15251, June 2021
Xu, R., Li, G., Yang, J., Lin, L.: Larger norm more transferable: an adaptive feature norm approach for unsupervised domain adaptation. In: ICCV, pp. 1426–1435 (2019)
Yang, X., Hou, L., Zhou, Y., Wang, W., Yan, J.: Dense label encoding for boundary discontinuity free rotation detection. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 15819–15829 (2021)
Yosinski, J., Clune, J., Bengio, Y., Lipson, H.: How transferable are features in deep neural networks? arXiv preprint arXiv:1411.1792 (2014)
You, K., Wang, X., Long, M., Jordan, M.: Towards accurate model selection in deep unsupervised domain adaptation. In: International Conference on Machine Learning, pp. 7124–7133. PMLR (2019)
Zhang, J., Ding, Z., Li, W., Ogunbona, P.: Importance weighted adversarial nets for partial domain adaptation. In: CVPR (2018)
Zhang, S., Wu, G., Costeira, J.P., Moura, J.M.: Understanding traffic density from large-scale web camera data. In: CVPR (2017)
Zhang, S., Tuo, H., Hu, J., Jing, Z.: Domain adaptive yolo for one-stage cross-domain detection. arXiv preprint arXiv:2106.13939 (2021)
Zhang, Y., Liu, T., Long, M., Jordan, M.: Bridging theory and algorithm for domain adaptation. In: International Conference on Machine Learning, pp. 7404–7413. PMLR (2019)
Zheng, Z., Yang, Y.: Rectifying pseudo label learning via uncertainty estimation for domain adaptive semantic segmentation. Int. J. Comput. Vision. 129, 1106–1120 (2021)
Zhong, H., Tuo, H., Wang, C., Ren, X., Hu, J., Qiao, L.: Source-constraint adversarial domain adaptation. In: 2019 IEEE International Conference on Image Processing (ICIP), pp. 2486–2490. IEEE (2019)
Zou, Z., Qu, X., Zhou, P., Xu, S., Ye, J.: Coarse to fine: Domain adaptive crowd counting via adversarial scoring network (2021)
Acknowledgement
This work was in part supported by Vision Semantics Limited, Alan Turing Institute, Open Research Projects of Zhejiang Lab (No. 2021KB0AB04), Zhejiang Provincial Natural Science Foundation of China (No. LQ21F020004), Natural Science Foundation of China (No. 61906176), and China Scholarship Council.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
1 Electronic supplementary material
Below is the link to the electronic supplementary material.
Rights and permissions
Copyright information
© 2022 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Hu, J., Zhong, H., Yang, F., Gong, S., Wu, G., Yan, J. (2022). Learning Unbiased Transferability for Domain Adaptation by Uncertainty Modeling. In: Avidan, S., Brostow, G., Cissé, M., Farinella, G.M., Hassner, T. (eds) Computer Vision – ECCV 2022. ECCV 2022. Lecture Notes in Computer Science, vol 13691. Springer, Cham. https://doi.org/10.1007/978-3-031-19821-2_13
Download citation
DOI: https://doi.org/10.1007/978-3-031-19821-2_13
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-19820-5
Online ISBN: 978-3-031-19821-2
eBook Packages: Computer ScienceComputer Science (R0)