Abstract
Domain adaptation (DA) has been a fundamental building block for Transfer Learning (TL) which assumes that source and target domain share the same label space. A more general and realistic setting is that the label space of target domain is a subset of the source domain, as termed by Partial domain adaptation (PDA). Previous methods typically match the whole source domain to target domain, which causes negative transfer due to the source-negative classes in source domain that does not exist in target domain. In this paper, a novel Discriminative Partial Domain Adversarial Network (DPDAN) is developed. We first propose to use hard binary weighting to differentiate the source-positive and source-negative samples in the source domain. The source-positive samples are those with labels shared by two domains, while the rest in the source domain are treated as source-negative samples. Based on the above binary relabeling strategy, our algorithm maximizes the distribution divergence between source-negative samples and all the others (source-positive and target samples), meanwhile minimizes domain shift between source-positive samples and target domain to obtain discriminative domain-invariant features. We empirically verify DPDAN can effectively reduce the negative transfer caused by source-negative classes, and also theoretically show it decreases negative transfer caused by domain shift. Experiments on four benchmark domain adaptation datasets show DPDAN consistently outperforms state-of-the-art methods.
H. Tuo—This work is supported by National Natural Science Foundation of China(Grant No.61673262 and 61175028) and Shanghai key project of basic research(Grant No.16JC1401100)
J. Yan—Partial work was done when Junchi Yan was with Tencent AI Lab as visiting scholar.
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
References
Cao, Z., Long, M., Wang, J., Jordan, M.I.: Partial transfer learning with selective adversarial networks. In: The IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2018)
Cao, Z., Ma, L., Long, M., Wang, J.: Partial adversarial domain adaptation. In: The European Conference on Computer Vision (ECCV) (2018)
Donahue, J., et al.: Decaf: a deep convolutional activation feature for generic visual recognition. In: International Conference on Machine Learning (ICML) (2014)
G. Cai, Y. Wang, M.Z.L.H.: Unsupervised domain adaptation with residual transfer networks. In: Advances in Neural Information Processing Systems (2016)
Ganin, Y., et al.: Domain-adversarial training of neural networks. J. Mach. Learn. Res. 17, 59:1–59:35 (2016)
Gong, B., Shi, Y., Sha, F., Grauman., K.: Geodesic flow kernel for unsupervised domain adaptation. In: IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2012)
Goodfellow, I., et al.: Generative adversarial nets (2014)
Griffin, G., Holub, A., Perona, P.: Caltech-256 object category dataset. Technical report (2007)
He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2016)
Hoffman, J., et al.: Cycada: cycleconsistent adversarial domain adaptation. In: Proceedings of the 35th International Conference on Machine Learning (ICML), vol. 2, pp. 1994–2003 (2018)
Krizhevsky, A., Sutskever, I., Hinton, G.E.: Imagenet classification with deep convolutional neural networks. In: Advances in Neural Information Processing Systems (NIPS) (2012)
Jain, L.P., Scheirer, W.J., Boult, T.E.: Multi-class open set recognition using probability of inclusion. In: Fleet, D., Pajdla, T., Schiele, B., Tuytelaars, T. (eds.) ECCV 2014. LNCS, vol. 8691, pp. 393–409. Springer, Cham (2014). https://doi.org/10.1007/978-3-319-10578-9_26
Long, J., Shelhamer, E., Darrell, T.: Fully convolutional networks for semantic segmentation. In: IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2015)
Long, M., Cao, Y., Wang, J., Jordan., M.I.: Learning transferable features with deep adaptation networks. In: Proceedings of the 34th International Conference on Machine Learning (ICML) (2015)
Long, M., Cao, Z., Wang, J., I, J.M.: Transferable features with deep adaptation networks. In: Proceedings of the 34th International Conference on Machine Learning (ICML) (2015)
Long, M., Zhu, H., Wang, J., Jordan., M.I.: Deep transfer learning with joint adaptation networks. In: Proceedings of the 34th International Conference on Machine Learning (ICML) (2017)
Luo, Z., Zou, Y., Hoffman, Y., Li, F.: Label efficient learning of transferable representations across domains and tasks. In: Advances in Neural Information Processing Systems (NIPS) (2017)
Otsu, N.: A threshold selection method from grey-level histograms. IEEE Trans. Syst. Man Cybern. 9, 62–66 (1979)
Pan, Y., Yao, T., Li, Y., Wang, Y., Ngo, C., Mei, T.: Transferable prototypical networks for unsupervised domain adaptation. In: IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2019)
Ren, S., He, K., Girshick, R., Sun, J.: Faster r-cnn:towards real-time object detection with region proposal networks. In: Advances in Neural Information Processing Systems, vol. 28, pp. 91–99 (2015)
Russakovsky, O., et al.: Imagenet large scale visual recognition challenge. Int. J. Comput. Vision (IJCV) 115, 211–252 (2015)
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., Saenko, K.: Universal domain adaptation through self-supervision. arXiv preprint (2020)
Sugiyama, M., Krauledat, M., Muller, K.R.: Covariate shift adaptation by importance weighted cross validation. J. Mach. Learn. Res. (JMLR) 8, 985–1005 (2007)
Tzeng, E., Hoffman, J., Saenko, K., Darrell, T.: Adversarial discriminative domain adaptation. In: IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2017)
Tzeng, E., Hoffman, J., Zhang, N., Saenko, K., Darrell., T.: Simultaneous deep transfer across domains and tasks. In: IEEE International Conference on Computer Vision (ICCV) (2015)
Venkateswara, H., Eusebio, J., Chakraborty, S., Panchanathan, S.: Deep hashing network for unsupervised domain adaptation. In: IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2017)
Wang, C., Tuo, H., Wang, J., Qiao, L.: Discriminative transfer learning via local and global structure preservation. Signal Image Video Process. 13(4), 753–760 (2019). https://doi.org/10.1007/s11760-018-1405-7
Peng, X., Usman, B., Kaushik, N., Hoffman, J., Wang, D., Saenko, K.: The visual domain adaptation challenge. arXiv preprint (2017)
Wang, X., Li, L., Wei, W., Long, M., Wang, J.: Transferable attention for domain adaptation. In: The Association for the Advance of Artificial Intelligence (AAAI) (2019)
Yosinski, J., Clune, J., Bengio, Y., Lipson, H.: How transferable are features in deep neural networks? In: Advances in Neural Information Processing Systems (NIPS) (2014)
Zhang, J., Ding, Z., Li, W., Ogunbona, P.: Importance weighted adversarial nets for partial domain adaptation. In: The IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2018)
Zhong, H., Tuo, H., Wang, C., Ren, X., Hu, J., Qiao, L.: Source-constraint adversarial domain adaptation, pp. 2486–2490 (2019). https://doi.org/10.1109/ICIP.2019.8803282
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
Hu, J. et al. (2020). Discriminative Partial Domain Adversarial Network. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, JM. (eds) Computer Vision – ECCV 2020. ECCV 2020. Lecture Notes in Computer Science(), vol 12372. Springer, Cham. https://doi.org/10.1007/978-3-030-58583-9_38
Download citation
DOI: https://doi.org/10.1007/978-3-030-58583-9_38
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-58582-2
Online ISBN: 978-3-030-58583-9
eBook Packages: Computer ScienceComputer Science (R0)