Importance Weighted Adversarial Nets for Partia Domain Adaptation

Authors

Jing Zhang, University of WollongongFollow
Zewei Ding, University of WollongongFollow
Wanqing Li, University of WollongongFollow
Philip O. Ogunbona, University of WollongongFollow

RIS ID

135905

Publication Details

Zhang, J., Ding, Z., Li, W. & Ogunbona, P. (2018). Importance Weighted Adversarial Nets for Partia Domain Adaptation. 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition (pp. 8156-8164). United States: IEEE.

Abstract

This paper proposes an importance weighted adversarial nets-based method for unsupervised domain adaptation, specific for partial domain adaptation where the target domain has less number of classes compared to the source domain. Previous domain adaptation methods generally assume the identical label spaces, such that reducing the distribution divergence leads to feasible knowledge transfer. However, such an assumption is no longer valid in a more realistic scenario that requires adaptation from a larger and more diverse source domain to a smaller target domain with less number of classes. This paper extends the adversarial nets-based domain adaptation and proposes a novel adversarial nets-based partial domain adaptation method to identify the source samples that are potentially from the outlier classes and, at the same time, reduce the shift of shared classes between domains.