Please use this identifier to cite or link to this item:
Title: Unsupervised domain adaptation in the wild via disentangling representation learning
Authors: Li, Haoliang
Wan, Renjie
Wang, Shiqi
Kot, Alex Chichung
Keywords: Engineering::Electrical and electronic engineering
Issue Date: 2021
Source: Li, H., Wan, R., Wang, S. & Kot, A. C. (2021). Unsupervised domain adaptation in the wild via disentangling representation learning. International Journal of Computer Vision, 129(2), 267-283.
Journal: International Journal of Computer Vision
Abstract: Most recently proposed unsupervised domain adaptation algorithms attempt to learn domain invariant features by confusing a domain classifier through adversarial training. In this paper, we argue that this may not be an optimal solution in the real-world setting (a.k.a. in the wild) as the difference in terms of label information between domains has been largely ignored. As labeled instances are not available in the target domain in unsupervised domain adaptation tasks, it is difficult to explicitly capture the label difference between domains. To address this issue, we propose to learn a disentangled latent representation based on implicit autoencoders. In particular, a latent representation is disentangled into a global code and a local code. The global code is capturing category information via an encoder with a prior, and the local code is transferable across domains, which captures the “style” related information via an implicit decoder. Experimental results on digit recognition, object recognition and semantic segmentation demonstrate the effectiveness of our proposed method.
ISSN: 0920-5691
DOI: 10.1007/s11263-020-01364-5
Schools: School of Electrical and Electronic Engineering 
Interdisciplinary Graduate School (IGS) 
Research Centres: Rapid-Rich Object Search (ROSE) Lab 
Rights: © 2020 Springer Science+Business Media, LLC, part of Springer Nature. All rights reserved.
Fulltext Permission: none
Fulltext Availability: No Fulltext
Appears in Collections:EEE Journal Articles
IGS Journal Articles

Citations 20

Updated on Dec 5, 2023

Web of ScienceTM
Citations 20

Updated on Oct 25, 2023

Page view(s)

Updated on Dec 7, 2023

Google ScholarTM




Items in DR-NTU are protected by copyright, with all rights reserved, unless otherwise indicated.