Jump to : Download | Abstract | Contact | BibTex reference | EndNote reference |


Dong Liu, Kuan-Ting Lai, Guangnan Ye, Ming-Syan Chen, Shih-Fu Chang. Sample Specific Late Fusion for Visual Category Recognition. In IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR), Portland, OR, June 2013.

Download [help]

Download paper: Adobe portable document (pdf)

Copyright notice:This material is presented to ensure timely dissemination of scholarly and technical work. Copyright and all rights therein are retained by authors or by other copyright holders. All persons copying this information are expected to adhere to the terms and constraints invoked by each author's copyright. These works may not be reposted without the explicit permission of the copyright holder.


Late fusion addresses the problem of combining the prediction scores of multiple classifiers, in which each score is predicted by a classifier trained with a specific feature. However, the existing methods generally use a fixed fusion weight for all the scores of a classifier, and thus fail to optimally determine the fusion weight for the individual samples. In this paper, we propose a sample-specific late fusion method to address this issue. Specifically, we cast the problem into an information propagation process which propagates the fusion weights learned on the labeled samples to individual unlabeled samples, while enforcing that positive samples have higher fusion scores than negative samples. In this process, we identify the optimal fusion weights for each sample and push positive samples to top positions in the fusion score rank list. We formulate our problem as a L_infinity norm constrained optimization problem and apply the Alternating Direction Method of Multipliers for the optimization. Extensive experiment results on various visual categorization tasks show that the proposed method consistently and significantly beats the state-of-the-art late fusion methods. To the best knowledge, this is the first method supporting sample-specific fusion weight learning


Dong Liu
Guangnan Ye
Shih-Fu Chang

BibTex Reference

   Author = {Liu, Dong and Lai, Kuan-Ting and Ye, Guangnan and Chen, Ming-Syan and Chang, Shih-Fu},
   Title = {Sample Specific Late Fusion for Visual Category Recognition},
   BookTitle = {IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR)},
   Address = {Portland, OR},
   Month = {June},
   Year = {2013}

EndNote Reference [help]

Get EndNote Reference (.ref)


For problems or questions regarding this web site contact The Web Master.

This document was translated automatically from BibTEX by bib2html (Copyright 2003 © Eric Marchand, INRIA, Vista Project).