Abstract
Universal domain adaptation (UniDA) transfers knowledge between domains without any constraint on the label sets, extending the applicability of domain adaptation in the wild. In UniDA, both the source and target label sets may hold individual labels not shared by the other domain. A de facto challenge of UniDA is to classify the target examples in the shared classes against the domain shift. A more prominent challenge of UniDA is to mark the target examples in the target-individual label set (open classes) as “unknown”. These two entangled challenges make UniDA a highly under-explored problem. Previous work on UniDA focuses on the classification of data in the shared classes and uses per-class accuracy as the evaluation metric, which is badly biased to the accuracy of shared classes. However, accurately detecting open classes is the mission-critical task to enable real universal domain adaptation. It further turns UniDA problem into a well-established close-set domain adaptation problem. Towards accurate open class detection, we propose Calibrated Multiple Uncertainties (CMU) with a novel transferability measure estimated by a mixture of uncertainty quantities in complementation: entropy, confidence and consistency, defined on conditional probabilities calibrated by a multi-classifier ensemble model. The new transferability measure accurately quantifies the inclination of a target example to the open classes. We also propose a novel evaluation metric called H-score, which emphasizes the importance of both accuracies of the shared classes and the “unknown” class. Empirical results under the UniDA setting show that CMU outperforms the state-of-the-art domain adaptation methods on all the evaluation metrics, especially by a large margin on the H-score.
B. Fu and Z. Cao—Equal contribution.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Busto, P.P., Iqbal, A., Gall, J.: Open set domain adaptation for image and action recognition. IEEE Trans. Pattern Anal. Mach. Intell. (2018)
Cao, Z., Long, M., Wang, J., Jordan, M.I.: Partial transfer learning with selective adversarial networks. In: CVPR, June 2018
Cao, Z., Ma, L., Long, M., Wang, J.: Partial adversarial domain adaptation. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) ECCV 2018. LNCS, vol. 11212, pp. 139–155. Springer, Cham (2018). https://doi.org/10.1007/978-3-030-01237-3_9
Cao, Z., You, K., Long, M., Wang, J., Yang, Q.: Learning to transfer examples for partial domain adaptation. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 2985–2994 (2019)
Chen, Q., Liu, Y., Wang, Z., Wassell, I., Chetty, K.: Re-weighted adversarial adaptation network for unsupervised domain adaptation. In: CVPR, pp. 7976–7985 (2018)
Deng, J., Dong, W., Socher, R., Li, L.J., Li, K., Fei-Fei, L.: ImageNet: a large-scale hierarchical image database. In: CVPR 2009 (2009)
Gal, Y., Ghahramani, Z.: Dropout as a Bayesian approximation: representing model uncertainty in deep learning. In: International Conference on Machine Learning, pp. 1050–1059 (2016)
Ganin, Y., et al.: Domain-adversarial training of neural networks. JMLR 17, 59:1–59:35 (2016)
Guo, C., Pleiss, G., Sun, Y., Weinberger, K.Q.: On calibration of modern neural networks. In: Proceedings of the 34th International Conference on Machine Learning, vol. 70, pp. 1321–1330. JMLR. org (2017)
He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: CVPR (2016)
Hu, J., Wang, C., Qiao, L., Zhong, H., Jing, Z.: Multi-weight partial domain adaptation. In: The British Machine Vision Conference (BMVC) (2019)
Hu, L., Kan, M., Shan, S., Chen, X.: Duplex generative adversarial network for unsupervised domain adaptation. In: CVPR, June 2018
Hu, Y., Stumpfe, D., Bajorath, J.: Computational exploration of molecular scaffolds in medicinal chemistry: miniperspective. J. Med. Chem. 59(9), 4062–4076 (2016)
Kang, G., Zheng, L., Yan, Y., Yang, Y.: Deep adversarial attention alignment for unsupervised domain adaptation: the benefit of target Expectation maximization. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) ECCV 2018. LNCS, vol. 11215, pp. 420–436. Springer, Cham (2018). https://doi.org/10.1007/978-3-030-01252-6_25
Konstantinos, B., Nathan, S., David, D., Dumitru, E., Dilip, K.: Unsupervised pixel-level domain adaptation with generative adversarial networks. In: CVPR, pp. 95–104 (2017)
Lakshminarayanan, B., Pritzel, A., Blundell, C.: Simple and scalable predictive uncertainty estimation using deep ensembles. In: Advances in Neural Information Processing Systems, pp. 6402–6413 (2017)
Lian, Q., Li, W., Chen, L., Duan, L.: Known-class aware self-ensemble for open set domain adaptation. arXiv preprint arXiv:1905.01068 (2019)
Liu, H., Cao, Z., Long, M., Wang, J., Yang, Q.: Separate to adapt: open set domain adaptation via progressive separation. In: The IEEE Conference on Computer Vision and Pattern Recognition (CVPR), June 2019
Liu, Y.C., Yeh, Y.Y., Fu, T.C., Wang, S.D., Chiu, W.C., Frank Wang, Y.C.: Detach and adapt: learning cross-domain disentangled deep representation. In: CVPR, June 2018
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 domain adversarial network. In: NeurIPS (2018)
Long, M., Zhu, H., Wang, J., Jordan, M.I.: Unsupervised domain adaptation with residual transfer networks. In: NeurIPS, pp. 136–144 (2016)
Maria Carlucci, F., Porzi, L., Caputo, B., Ricci, E., Rota Bulo, S.: Autodial: automatic domain alignment layers. In: ICCV, October 2017
Murez, Z., Kolouri, S., Kriegman, D., Ramamoorthi, R., Kim, K.: Image to image translation for domain adaptation. In: CVPR, June 2018
Panareda Busto, P., Gall, J.: Open set domain adaptation. In: ICCV, October 2017
Peng, X., Bai, Q., Xia, X., Huang, Z., Saenko, K., Wang, B.: Moment matching for multi-source domain adaptation. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 1406–1415 (2019)
Peng, X., et al.: VisDA: a synthetic-to-real benchmark for visual domain adaptation. In: CVPR Workshops, pp. 2021–2026 (2018)
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., Watanabe, K., Ushiku, Y., Harada, T.: Maximum classifier discrepancy for unsupervised domain adaptation. In: CVPR, June 2018
Saito, K., Yamamoto, S., Ushiku, Y., Harada, T.: Open set domain adaptation by backpropagation. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) ECCV 2018. LNCS, vol. 11209, pp. 156–171. Springer, Cham (2018). https://doi.org/10.1007/978-3-030-01228-1_10
Sankaranarayanan, S., Balaji, Y., Castillo, C.D., Chellappa, R.: Generate to adapt: aligning domains using generative adversarial networks. In: CVPR, June 2018
Snoek, J., et al.: Can you trust your model’s uncertainty? Evaluating predictive uncertainty under dataset shift. In: Advances in Neural Information Processing Systems, pp. 13969–13980 (2019)
Tzeng, E., Hoffman, J., Saenko, K., Darrell, T.: Adversarial discriminative domain adaptation. In: CVPR (2017)
Tzeng, E., Hoffman, J., Zhang, N., Saenko, K., Darrell, T.: Deep domain confusion: Maximizing for domain invariance. arXiv preprint arXiv:1412.3474 (2014)
Venkateswara, H., Eusebio, J., Chakraborty, S., Panchanathan, S.: Deep hashing network for unsupervised domain adaptation. In: CVPR (2017)
Vittorio, F., Alina, K., Rodrigo, B., Victor, G., Matteo, M.: Open images challenge 2019 (2019). https://storage.googleapis.com/openimages/web/challenge2019.html
Volpi, R., Morerio, P., Savarese, S., Murino, V.: Adversarial feature augmentation for unsupervised domain adaptation. In: CVPR, June 2018
Wu, A., Nowozin, S., Meeds, E., Turner, R., Hernández-Lobato, J., Gaunt, A.: Deterministic variational inference for robust Bayesian neural networks. In: 7th International Conference on Learning Representations, ICLR 2019 (2019)
Wu, Z., et al.: Moleculenet: a benchmark for molecular machine learning. Chem. Sci. 9(2), 513–530 (2018)
Xie, S., Zheng, Z., Chen, L., Chen, C.: Learning semantic representations for unsupervised domain adaptation. In: ICML, pp. 5423–5432 (2018)
You, K., Long, M., Cao, Z., Wang, J., Jordan, M.I.: Universal domain adaptation. In: The IEEE Conference on Computer Vision and Pattern Recognition (CVPR), June 2019
You, K., Wang, X., Long, M., Jordan, M.: Towards accurate model selection in deep unsupervised domain adaptation. In: ICML, pp. 7124–7133 (2019)
Zhang, H., Li, A., Han, X., Chen, Z., Zhang, Y., Guo, Y.: Improving open set domain adaptation using image-to-image translation. In: 2019 IEEE International Conference on Multimedia and Expo (ICME), pp. 1258–1263. IEEE (2019)
Zhang, J., Ding, Z., Li, W., Ogunbona, P.: Importance weighted adversarial nets for partial domain adaptation. In: CVPR, June 2018
Zhang, W., Ouyang, W., Li, W., Xu, D.: Collaborative and adversarial network for unsupervised domain adaptation. In: CVPR, June 2018
Acknowledgement
This work was supported by the Natural Science Foundation of China (61772299, 71690231), and China University S&T Innovation Plan Guided by the Ministry of Education.
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
© 2020 Springer Nature Switzerland AG
About this paper
Cite this paper
Fu, B., Cao, Z., Long, M., Wang, J. (2020). Learning to Detect Open Classes for Universal Domain Adaptation. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, JM. (eds) Computer Vision – ECCV 2020. ECCV 2020. Lecture Notes in Computer Science(), vol 12360. Springer, Cham. https://doi.org/10.1007/978-3-030-58555-6_34
Download citation
DOI: https://doi.org/10.1007/978-3-030-58555-6_34
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-58554-9
Online ISBN: 978-3-030-58555-6
eBook Packages: Computer ScienceComputer Science (R0)