CASIA OpenIR  > 模式识别国家重点实验室  > 机器人视觉
SOSNet: Second Order Similarity Regularization for Local Descriptor Learning
Yurun Tian1,2; Xin Yu3; Bin Fan1; Fuchao Wu1; Huub Heijen4; Vassileios Balntas4
2019-06
Conference NameIEEE Conference on Computer Vision and Pattern Recognition (CVPR)
Conference Date2019-6
Conference Place美国 长滩
Abstract

Despite the fact that Second Order Similarity(SOS) has been used with significant success in tasks such as graph matching and clustering, it has not been exploited for learning local descriptors.
In this work, we explore the potential of SOS in the field of descriptor learning by building upon the intuition that a positive pair of matching points should exhibit similar distances with respect to other points in the embedding space. 
Thus, we propose a novel regularization term, named Second Order Similarity Regularization(SOSR), that follows this principle. 
By incorporating SOSR into training, our learned descriptor achieves state-of-the-art performance on several challenging benchmarks containing distinct tasks ranging from local patch retrieval to structure from motion. 
Furthermore, by designing a von Mises-Fischer distribution based evaluation method, we link the utilization of the descriptor space to the matching performance, thus demonstrating the effectiveness of our proposed SOSR.
Extensive experimental results, empirical evidence, and in-depth analysis are provided, indicating that SOSR can significantly boost the matching performance of the learned descriptor. 

Indexed ByEI
Document Type会议论文
Identifierhttp://ir.ia.ac.cn/handle/173211/23810
Collection模式识别国家重点实验室_机器人视觉
Corresponding AuthorBin Fan
Affiliation1.中国科学院自动化研究所
2.中国科学院大学
3.澳大利亚国立大学
4.Scape Technologies, UK
First Author AffilicationInstitute of Automation, Chinese Academy of Sciences
Corresponding Author AffilicationInstitute of Automation, Chinese Academy of Sciences
Recommended Citation
GB/T 7714
Yurun Tian,Xin Yu,Bin Fan,et al. SOSNet: Second Order Similarity Regularization for Local Descriptor Learning[C],2019.
Files in This Item: Download All
File Name/Size DocType Version Access License
sosnet_cvpr2019.pdf(681KB)会议论文 开放获取CC BY-NC-SAView Download
Related Services
Recommend this item
Bookmark
Usage statistics
Export to Endnote
Google Scholar
Similar articles in Google Scholar
[Yurun Tian]'s Articles
[Xin Yu]'s Articles
[Bin Fan]'s Articles
Baidu academic
Similar articles in Baidu academic
[Yurun Tian]'s Articles
[Xin Yu]'s Articles
[Bin Fan]'s Articles
Bing Scholar
Similar articles in Bing Scholar
[Yurun Tian]'s Articles
[Xin Yu]'s Articles
[Bin Fan]'s Articles
Terms of Use
No data!
Social Bookmark/Share
File name: sosnet_cvpr2019.pdf
Format: Adobe PDF
All comments (0)
No comment.
 

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