Learning Cross-Domain Feature Disentanglement with Supervision from A Single Domain

• Main Authors: Yen-Cheng Liu, 劉彥成
• Other Authors: Sheng-De Wang
• Format: Others
• Language: en_US
• Published: 2017
• Online Access: http://ndltd.ncl.edu.tw/handle/33b7b9

碩士 === 國立臺灣大學 === 電機工程學研究所 === 105 === The recent progress and development of deep generative models have led to remarkable improvements in research topics in computer vision and machine learning. In this article, the task of cross-domain feature disentanglement is addressed. This thesis advances the idea of unsupervised domain adaptation and propose to perform joint feature disentanglement and adaptation. Based on generative adversarial networks, a novel deep learning architecture with disentanglement ability is presented, which observes cross-domain image data and derives latent features with the underlying factors(e.g., attributes). As a result, our generative model is able to address cross-domain feature disentanglement with only the (attribute) supervision from the source-domain data (not the target-domain ones). In the experiments, the model is applied for generating and classifying images with particular attributes, and show that satisfactory results can be produced.