VALSE 首页 活动通知 好文作者面授招 查看内容

20161026-36 朱鹏飞:Feature oriented Self-representation and its applications .. ...

2016-10-22 17:18| 发布者: 程一-计算所| 查看: 7043| 评论: 0

摘要: 报告嘉宾2:朱鹏飞 (天津大学)报告时间:2016年10月26日(星期三)晚21:00(北京时间)报告题目:Feature oriented Self-representation and its applications主持人:任传贤(中山大学)报告摘要:Almost all the ...

报告嘉宾2:朱鹏飞 (天津大学)
报告题目:Feature oriented Self-representation and its applications 

Almost all the existing representation based classifiers represent a query sample as a linear combination of training samples, and their time and memory cost will increase rapidly with the number of training samples. We investigate the representation based classification problem from a rather different perspective in this paper, that is, we learn how each feature (i.e., each element) of a sample can be represented by the features of itself. Such a self-representation property of sample features can be readily employed for pattern classification and a novel self-representation induced classifier (SRIC) is proposed. SRIC learns a self-representation matrix for each class. Given a query sample, its self-representation residual can be computed by each of the learned self-representation matrices, and classification can then be performed by comparing these residuals. In light of the principle of SRIC, a discriminative SRIC (DSRIC) method is developed. For each class, a discriminative self-representation matrix is trained to minimize the self-representation residual of this class while representing little the features of other classes. Experimental results on different pattern recognition tasks show that DSRIC achieves comparable or superior recognition rate to state-of-the-art representation based classifiers, however, it is much more efficient and needs much less storage space.

[1]Zhu P, Zhang L, Zuo W, et al. A Self-representation induced Classifier[C]// IJCAI. 2016.  
[2]Zhu P, Hu Q, Zhang C, et al. Coupled Dictionary Learning for Unsupervised Feature Selection[C]//Thirtieth AAAI Conference on Artificial Intelligence. 2016. 
[3]Zhu P, Zuo W, Zhang L, et al. Unsupervised feature selection by regularized self-representation[J]. Pattern Recognition, 2015, 48(2): 438-446.

朱鹏飞,分别于2009和2011年在哈尔滨工业大学能源科学与工程学院获得学士和硕士学位,2015年05月于香港理工大学电子计算学系获得博士学位。随后到天津大学计算机科学与技术学院工作,任副教授和硕士生导师,主要研究方向是机器学习和计算机视觉。目前,发表论文30余篇,包括AAAI、IJCAI、ICCV、ECCV以及IEEE Transactions on Information Forensics and Security等。近几年,担任IJCRS 2016、 CCML 2017、CCCV 2017本地组织主席。2015年获得黑龙江省高校自然科学一等奖(排名第五),2016年获得黑龙江自然科学一等奖(排名第五)。



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

GMT+8, 2022-1-22 04:41 , Processed in 0.010987 second(s), 15 queries .

Powered by Discuz! X3.4

Copyright © 2001-2020, Tencent Cloud.