標題: Detach and Adapt: Learning Cross-Domain Disentangled Deep Representation
作者: Liu, Yen-Cheng
Yeh, Yu-Ying
Fu, Tzu-Chien
Wang, Sheng-De
Chiu, Wei-Chen
Wang, Yu-Chiang Frank
資訊工程學系
Department of Computer Science
公開日期: 1-Jan-2018
摘要: While representation learning aims to derive interpretable features for describing visual data, representation disentanglement further results in such features so that particular image attributes can be identified and manipulated. However, one cannot easily address this task without observing ground truth annotation for the training data. To address this problem, we propose a novel deep learning model of Cross-Domain Representation Disentangler (CDRD). By observing fully annotated source-domain data and unlabeled target-domain data of interest, our model bridges the information across data domains and transfers the attribute information accordingly. Thus, cross-domain feature disentanglement and adaptation can be jointly performed. In the experiments, we provide qualitative results to verify our disentanglement capability. Moreover, we further confirm that our model can be applied for solving classification tasks of unsupervised domain adaptation, and performs favorably against state-of-the-art image disentanglement and translation methods.
URI: http://dx.doi.org/10.1109/CVPR.2018.00924
http://hdl.handle.net/11536/151020
ISSN: 1063-6919
DOI: 10.1109/CVPR.2018.00924
期刊: 2018 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR)
起始頁: 8867
結束頁: 8876
Appears in Collections:Conferences Paper