设为首页收藏本站

VALSE

VALSE 首页 活动通知 好文作者面授招 查看内容

20170920-22:李文 Domain Generalization and Adaptation using Low...

2017-9-14 18:44| 发布者: 程一-计算所| 查看: 1416| 评论: 0

摘要: 报告嘉宾:李文(苏黎世联邦理工学院)报告时间:2017年9月20日(星期三)晚20:00(北京时间)报告题目:Domain Generalization and Adaptation using Low Rank Exemplar Classifiers主持人: 阚美娜(中科院计算所 ...

报告嘉宾:李文(苏黎世联邦理工学院)

报告时间:2017年9月20日(星期三)晚20:00(北京时间)

报告题目:Domain Generalization and Adaptation using Low Rank Exemplar Classifiers

主持人:  阚美娜(中科院计算所)


报告摘要:

Domain adaptation between diverse source and target domains is a challenging research problem, especially in the real-world visual recognition tasks where the images and videos consist of significant variations in viewpoints, illuminations, qualities, etc. In this paper, we propose a new approach for domain generalization and domain adaptation based on exemplar SVMs. Specifically, we decompose the source domain into many subdomains, each of which contains only one positive training sample and all negative samples. Each subdomain is relatively less diverse, and is expected to have a simpler distribution. By training one exemplar SVM for each subdomain, we obtain a set of exemplar SVMs. To further exploit the inherent structure of source domain, we introduce a nuclear-norm based regularizer into the objective function in order to enforce the exemplar SVMs to produce a low-rank output on training samples. In the prediction process, the confident exemplar SVM classifiers are selected and reweigted according to the distribution mismatch between each subdomain and the test sample in the target domain. We formulate our approach based on the logistic regression and least square SVM algorithms, which are referred to as low rank exemplar SVMs (LRE-SVMs) and low rank exemplar least square SVMs (LRE-LSSVMs), respectively. A fast algorithm is also developed for accelerating the training of LRE-LSSVMs. We further extend Domain Adaptation Machine (DAM) to learn an optimal target classifier for domain adaptation, and show that our approach can also be applied to domain adaptation with evolving target domain, where the target data distribution is gradually changing. The comprehensive experiments for object recognition and action recognition demonstrate the effectiveness of our approach for domain generalization and domain adaptation with fixed and evolving target domains.


参考文献:

Wen Li, Zheng Xu, Dong Xu, Dengxin Dai, and Luc Van Gool. Domain Generalization and Adaptation using Low Rank Exemplar SVMs. In T-PAMI, 2017 (In Press). 

Zheng Xu, Wen Li, Li Niu, and Dong Xu. Exploiting Low-rank Structure from Latent Domains for Domain Generalization. In ECCV, 2014.


报告人简介:

李文博士目前在苏黎世联邦理工学院(ETH Zurich)计算机视觉实验室任博士后,其合作导师为Luc Van Gool教授。李文博士2015年于新加坡南洋理工大学获得博士学位,导师为徐东教授。其研究方向主要包括迁移学习(Transfer Learning)、弱监督学习(Weakly Supervised Leanring)、多视角学习(Multiple View Learning)、特有信息学习(Learning Using Privileged Information)及在计算机视觉中的应用,先后在T-PAMI、IJCV、T-IP、TNN、CVPR、ICCV、ECCV、IJCAI等知名国际期刊与会议上发表学术论文20余篇,谷歌学术引用超过700次。李文博士为CVPR2017 WebVision基于网络数据学习的大规模图像识别竞赛的主要发起人之一。其还多次作为组织者之一在ICCV、ECCV、ICDM等会议上组办迁移学习相关workshop。更多信息详见:http://www.vision.ee.ethz.ch/~liwenw/


特别鸣谢本次Webinar主要组织者:

VOOC责任委员:阚美娜(中科院计算所)

VODB协调理事:贾伟(合肥工业大学)



最新评论

Archiver|手机版|小黑屋|Vision And Learning SEminar    

GMT+8, 2017-11-24 13:21 , Processed in 0.026520 second(s), 19 queries .

Powered by Discuz! X3.2

© 2001-2013 Comsenz Inc.

返回顶部