UCL Discovery
UCL home » Library Services » Electronic resources » UCL Discovery

Re-Weighted Adversarial Adaptation Network for Unsupervised Domain Adaptation

Chen, Q; Yang, L; Zhaowen, W; Wassell, I; Chetty, K; (2018) Re-Weighted Adversarial Adaptation Network for Unsupervised Domain Adaptation. In: CVPR 2018, IEEE Conference on Computer Vision and Pattern Recognition. (pp. pp. 7976-7985). IEEE (In press). Green open access

[thumbnail of CVPR 2018.pdf]
Preview
Text
CVPR 2018.pdf - Published Version

Download (638kB) | Preview

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.

Type: Proceedings paper
Title: Re-Weighted Adversarial Adaptation Network for Unsupervised Domain Adaptation
Event: CVPR 2018, IEEE Conference on Computer Vision and Pattern Recognition, 18-22 June 2018, Salt Lake City, USA
Location: Salt Lake City, USA
Dates: 18 June 2018 - 22 June 2018
Open access status: An open access version is available from UCL Discovery
Publisher version: http://openaccess.thecvf.com/content_cvpr_2018/htm...
Language: English
Additional information: This version is the author accepted manuscript. For information on re-use, please refer to the publisher’s terms and conditions.
UCL classification: UCL
UCL > Provost and Vice Provost Offices > UCL BEAMS
UCL > Provost and Vice Provost Offices > UCL BEAMS > Faculty of Engineering Science
UCL > Provost and Vice Provost Offices > UCL BEAMS > Faculty of Engineering Science > Dept of Security and Crime Science
URI: https://discovery.ucl.ac.uk/id/eprint/10051155
Downloads since deposit
222Downloads
Download activity - last month
Download activity - last 12 months
Downloads by country - last 12 months

Archive Staff Only

View Item View Item