CASIA OpenIR  > 模式识别国家重点实验室  > 生物识别与安全技术研究
Large Scale Similarity Learning Using Similar Pairs for Person Verification
Yang Yang(杨阳); Shengcai Liao; Zhen Lei; Stan Z. Li; Yang Yang
Conference NameAssociation for the Advancement of Artificial Intelligence
Source PublicationAAAI
Conference Date2016, 02.12-02.17
Conference PlacePhoenix, USA
In this paper, we propose a novel similarity measure and then
introduce an efficient strategy to learn it by using only similar
pairs for person verification. Unlike existing metric learning
methods, we consider both the difference and commonness of
an image pair to increase its discriminativeness. Under a pairconstrained
Gaussian assumption, we show how to obtain the
Gaussian priors (i.e., corresponding covariance matrices) of
dissimilar pairs from those of similar pairs. The application
of a log likelihood ratio makes the learning process simple
and fast and thus scalable to large datasets. Additionally, our
method is able to handle heterogeneous data well. Results on
the challenging datasets of face verification (LFW and Pub-
Fig) and person re-identification (VIPeR) show that our algorithm
outperforms the state-of-the-art methods.
KeywordPerson Re-identification Face Verification Large Scale Similarity Learning
Document Type会议论文
Corresponding AuthorYang Yang
Recommended Citation
GB/T 7714
Yang Yang,Shengcai Liao,Zhen Lei,et al. Large Scale Similarity Learning Using Similar Pairs for Person Verification[C],2016.
Files in This Item: Download All
File Name/Size DocType Version Access License
AAAI16_LSSL.pdf(539KB)会议论文 开放获取CC BY-NC-SAView Download
Related Services
Recommend this item
Usage statistics
Export to Endnote
Google Scholar
Similar articles in Google Scholar
[Yang Yang(杨阳)]'s Articles
[Shengcai Liao]'s Articles
[Zhen Lei]'s Articles
Baidu academic
Similar articles in Baidu academic
[Yang Yang(杨阳)]'s Articles
[Shengcai Liao]'s Articles
[Zhen Lei]'s Articles
Bing Scholar
Similar articles in Bing Scholar
[Yang Yang(杨阳)]'s Articles
[Shengcai Liao]'s Articles
[Zhen Lei]'s Articles
Terms of Use
No data!
Social Bookmark/Share
File name: AAAI16_LSSL.pdf
Format: Adobe PDF
All comments (0)
No comment.

Items in the repository are protected by copyright, with all rights reserved, unless otherwise indicated.