Re-weighted Adversarial Adaptation Network for Unsupervised Domain Adaptation
Authors:
- Qingchao ChenQCQingchao Chen
- Yang LiuYLYang Liu
- Zhaowen WangZWZhaowen Wang
- Ian WassellIWIan Wassell
- Kevin ChettyKCKevin Chetty
- 1 June 2018
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 7976-7985
Abstract
Unsupervised Domain Adaptation (UDA) aims to transfer domain knowledge from existing well-defined tasks to new ones where labels are unavailable. In the real-world applications, as the domain (task) discrepancies are usually uncontrollable, it is significantly motivated to match the feature distributions even if the domain discrepancies are disparate. Additionally, as no label is available in the target domain, how to successfully adapt the classifier from the source to the target domain still remains an open question. In this paper, we propose the Re-weighted Adversarial Adaptation Network (RAAN) to reduce the feature distribution divergence and adapt the classifier when domain discrepancies are disparate. Specifically, to alleviate the need of common supports in matching the feature distribution, we choose to minimize optimal transport (OT) based Earth-Mover (EM) distance and reformulate it to a minimax objective function. Utilizing this, RAAN can be trained in an end-to-end and adversarial manner. To further adapt the classifier, we propose to match the label distribution and embed it into the adversarial training. Finally, after extensive evaluation of our method using UDA datasets of varying difficulty, RAAN achieved the state-of-the-art results and outperformed other methods by a large margin when the domain shifts are disparate.Keywords
This publication has 13 references indexed in Scilit:
- Deep Hashing Network for Unsupervised Domain Adaptation2017
- Adversarial Discriminative Domain Adaptation2017
- Optimal Transport for Domain AdaptationIEEE Transactions on Pattern Analysis and Machine Intelligence, 2016
- Transfer Joint Matching for Unsupervised Domain Adaptation2014
- Contour Detection and Hierarchical Image SegmentationIEEE Transactions on Pattern Analysis and Machine Intelligence, 2010
- A theory of learning from different domainsMachine Learning, 2009
- A Survey on Transfer LearningIEEE Transactions on Knowledge and Data Engineering, 2009
- Gradient-based learning applied to document recognitionProceedings of the IEEE, 1998
- A classification EM algorithm for clustering and two stochastic versionsComputational Statistics & Data Analysis, 1992
- On the Translocation of MassesManagement Science, 1958