標題: ADVERSARIAL DOMAIN SEPARATION AND ADAPTATION
作者: Tsai, Jen-Chieh
Chien, Jen-Tzung
電機工程學系
Department of Electrical and Computer Engineering
關鍵字: Deep learning;domain adaptation;latent features;adversarial learning;pattern classification
公開日期: 1-一月-2017
摘要: Traditional domain adaptation methods attempted to learn the shared representation for distribution matching between source domain and target domain where the individual information in both domains was not characterized. Such a solution suffers from the mixing problem of individual information with the shared features which considerably constrains the performance for domain adaptation. To relax this constraint, it is crucial to extract both shared information and individual information. This study captures both information via a new domain separation network where the shared features are extracted and purified via separate modeling of individual information in both domains. In particular, a hybrid adversarial learning is incorporated in a separation network as well as an adaptation network where the associated discriminators are jointly trained for domain separation and adaptation according to the minmax optimization over separation loss and domain discrepancy, respectively. Experiments on different tasks show the merit of using the proposed adversarial domain separation and adaptation.
URI: http://hdl.handle.net/11536/146956
ISSN: 2161-0363
期刊: 2017 IEEE 27TH INTERNATIONAL WORKSHOP ON MACHINE LEARNING FOR SIGNAL PROCESSING
顯示於類別:會議論文