演講者：葉倚任教授 

　　　　國立高雄師範大學數學系

日　期：2016年11月16日（星期三） 15:30

地　點：國立高雄大學理學院320室

講　題：Domain Adaptation for Visual Classification

摘　要：

For cross-view action recognition and many real-world visual classification problems, one needs to recognize test data at a particular target domain of interest, while training data are collected at a different source domain. Without eliminating such domain differences, recognition of test data using classifiers trained in the source domain will not be expected to produce satisfactory performance. In this talk, I will introduce several domain adaptation approaches, which are able to learn a common feature space relating cross-domain data. In particular, our proposed method (among one of these approaches) not only aims at matching cross-domain data marginal distributions during adaptation, but also exploits the structure of target domain data and update class-conditional distributions accordingly. Experiments on various cross-domain visual classification tasks would verify the effectiveness and robustness of our proposed method.

本場演講與本校統計學研究所及巨量數據中心合辦