Abstract
A popular formulation of domain adaptation (DA) is to simultaneously minimize the source risk and the cross-domain discrepancy between the source domain \(\mathcal {D}_s\) and target domain \(\mathcal {D}_t\). However, this is believed to be suboptimal since the shared feature, which is indistinguishable by a domain classifier, could be far from optimum for the purpose of classification. In this paper, we propose an iterative DA framework for directly optimizing the classification error, which provides DA solutions to both unsupervised and semi-supervised scenarios. Instead of directly attacking \(\mathcal {D}_s \rightarrow \mathcal {D}_t\), we employ an iterative self-training approach of \(\mathcal {D}_s + \mathcal {D}_t^{l-1} \rightarrow \mathcal {D}_t^l\) for progressively-labelling of \(\mathcal {D}_t\) with the aim of \(\lim _{l\rightarrow \infty }\mathcal {D}_t^l \approx \mathcal {D}_t\). For unsupervised DA, it performs comparable to the state-of-the-art DA methods. In particular, it performs the best among various unsupervised DA methods for the very difficult task MNIST \(\rightarrow \) SVHN. By employing a few labeled samples in the target domain, we show that it can achieve significantly improved performance. For MNIST \(\rightarrow \) SVHN, the use of 60 labeled samples from SVHN is able to improve the accuracy margin about \(+10\%\) over the state-or-the-art unsupervised DA method. For a comparison with semi-supervised learning methods, it achieves the accuracy margin about \(+30\%\) over Mean Teacher with 60 labeled samples in SVHN.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Notes
- 1.
In [16], the authors reported the accuracy of just one trial and the accuracy was 52.8%.
References
Tarvainen, A., Valpola, H.: Mean teachers are better role models: weight-averaged consistency targets improve semi-supervised deep learning results. In: NIPS (2017)
Bousmalis, K., Trigeorgis, G., Silberman, N., Krishnan, D., Erhan, D.: Domain separation networks. In: NIPS (2016)
Chen, M., Weinberger, K.Q., Blitzer, J.: Co-training for domain adaptation. In: NIPS (2011)
Ganin, Y., Lempitsky, V.: Unsupervised domain adaptation by backpropagation. In: ICML (2015)
Goodfellow, I., et al.: Generative adversarial nets. In: NIPS (2014)
Gretton, A., Smola, A., Huang, J., Borgwardt, K.M., Schölkopf, B.: Covariate shift and local learning by distribution matching. In: Quiñonero-Candela, J., Sugiyama, M., Schwaighofer, A., Lawrence, N.D. (eds.) Dataset Shift in Machine Learning, pp. 131–160. MIT Press, Cambridge (2009)
He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: CVPR (2016)
Huang, G., Liu, Z., van der Maaten, L., Weinberger, K.Q.: Densely connected convolutional networks. In: CVPR (2017)
LeCun, Y., Bottou, L., Bengio, Y., Haffner, P.: Gradient-based learning applied to document recognition. Proc. IEEE 86(11), 2278–2324 (1998)
Lee, D.-H.: Pseudo-label: the simple and efficient semi-supervised learning method for deep neural networks. In: ICML Workshop on Challenges in Representation Learning (2013)
Long, M., Cao, Y., Wang, J., Jordan, M.I.: Learning transferable features with deep adaptation networks. In: ICML (2015)
Morerio, P., Cavazza, J., Murino, V.: Minimal-entropy correlation allignment for unsupervised deep domain adaptation. In: ICLR (2018)
Netzer, Y., Wang, T., Coates, A., Bissacco, A., Wu, B., Ng, A.Y.: Reading digits in natural images with unsupervised feature learning. In: NIPS (2011)
Nigam, K., Mccallum, A.K., Thrun, S., Mitchell, T.: Text classification from labeled and unlabeled documents using EM. Mach. Learn. 39, 103–104 (2000)
Rohrbach, M., Ebert, S., Schiele, B.: Transfer learning in a transductive setting. In: NIPS (2013)
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 (2018)
Sener, O., Song, H.O., Saxena, A., Savarese, S.: Learning transferrable representations for unsupervised domain adaptation. In: NIPS (2016)
Sun, B., Saenko, K.: Deep CORAL: correlation alignment for deep domain adaptation. In: ICCV Workshop on Transferring and Adapting Source Knowledge in Computer Vision (2016)
Tzeng, E., Hoffman, J., Zhang, N., Saenko, K.: Deep domain confusion: maximizing for domain invariance. arXiv:1412.3474 (2014)
Tzeng, E., Hoffman, J., Saenko, K., Darrell, T.: Adversarial discriminative domain adaptation. In: CVPR (2017)
Zhou, Z.-H., Li, M.: Tri-training: exploiting unlabeled data using three classifiers. TKDE 17(11), 1529–1541 (2005)
Zhu, X.: Semi-supervised learning literature survey. Technical report, University of Wisconsin-Madison (2008)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2019 Springer Nature Switzerland AG
About this paper
Cite this paper
Wu, X., Fu, J., Zhang, S., Zhou, Q. (2019). Iterative Discriminative Domain Adaptation. In: Lin, Z., et al. Pattern Recognition and Computer Vision. PRCV 2019. Lecture Notes in Computer Science(), vol 11857. Springer, Cham. https://doi.org/10.1007/978-3-030-31654-9_30
Download citation
DOI: https://doi.org/10.1007/978-3-030-31654-9_30
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-31653-2
Online ISBN: 978-3-030-31654-9
eBook Packages: Computer ScienceComputer Science (R0)