当前位置: 首页 > 科学研究 > 学术交流 > 正文
学术交流

Cross-dataset Visual Recognition

2019-12-25 11:16

报告人: 厉万庆

报告人单位: Motorola Research Lab

时间: 2019-12-26 14:00-17:00

地点: 数学学院32-B120房间

开始时间: 14:00

报告人简介: 教授

年: 2019

日月: 12.26

This talk takes a problem-oriented perspective and presents an overview of transfer-learning methods, both shallow and deep, for cross-dataset visual recognition. Specifically, itcategorisesthe cross dataset recognition into 17 problems based on a set of carefully chosen data and label attributes. Such a problem-oriented taxonomy has allowed us to examine how different transfer-learning approaches tackle each problem and how well each problem has been researched to date. This study has not only revealed the challenges in transfer learning for visual recognition but also the problems (e.g., 8 of the 17 problems) that have been scarcely studied. Also presented in this talk are two recently developed domain adaption methods, one is the joint geometrical and statistical alignment (JGSA) method and the other is adversarial nets-based unsupervised partial domain adaption.



联系我们

地址:天津市海河教育园区雅观路135号32号教学楼,300350
邮箱: maths@tju.edu.cn
电话:+86(0)22 27402850
传真:+86(0)22 27402850

扫码关注学院最新动态