UM  > Faculty of Science and Technology
Sharing model with multi-level feature representations
Li Shen1; Gang Sun1,2; Shuhui Wang3; Enhua Wu2,4; Qingming Huang1,3
2017-07-06
Conference NameIEEE International Conference on Image Processing (ICIP)
Source Publication2014 IEEE International Conference on Image Processing (ICIP)
Pages5931-5935
Conference Date27-30 Oct. 2014
Conference PlaceParis, France
Author of SourceInstitute of Electrical and Electronics Engineers Inc.
Abstract

Hierarchical classification models have been proposed to achieve high accuracy by transferring effective information across the categories. One important challenge for this paradigm is to design what can be transferred across the categories. In this paper, we propose a novel method to learn a sharing model by taking advantage of multi-level feature representations. Unlike many of the existing methods which learn the sharing model based on identical feature space, multi-level feature detectors enable our model to capture rich visual information in hierarchical category structure. Moreover, hierarchical classifier parameters associated with multi-level feature representations are learned to model the visual correlation in the hierarchy. The experimental results on Caltech-256 dataset and ImageNet subset demonstrate that our method achieves excellent performance compared with some state-of-the-art methods, and shows the advantage of multi-level information transfer. © 2014 IEEE.

DOI10.1109/ICIP.2014.7026198
Indexed BySCI
Language英语
WOS Research AreaComputer Science ; Engineering ; Imaging Science & Photographic Technology
WOS SubjectComputer Science, Theory & Methods ; Engineering, Electrical & Electronic ; Imaging Science & Photographic Technology
WOS IDWOS:000370063606020
Fulltext Access
Citation statistics
Cited Times [WOS]:0   [WOS Record]     [Related Records in WOS]
Document TypeConference paper
CollectionFaculty of Science and Technology
Affiliation1.University of Chinese Academy of Sciences, Beijing, China
2.State Key Lab. of Computer Science, Inst. of Software, CAS, Beijing, China;
3.Key Lab of Intelligent Information Processing of Chinese Academy of Sciences (CAS), Institute of Computing Technology, CAS, Beijing; 100190, China;
4.University of Macau, China
Recommended Citation
GB/T 7714
Li Shen,Gang Sun,Shuhui Wang,et al. Sharing model with multi-level feature representations[C]//Institute of Electrical and Electronics Engineers Inc.,2017:5931-5935.
Files in This Item:
There are no files associated with this item.
Related Services
Recommend this item
Bookmark
Usage statistics
Export to Endnote
Google Scholar
Similar articles in Google Scholar
[Li Shen]'s Articles
[Gang Sun]'s Articles
[Shuhui Wang]'s Articles
Baidu academic
Similar articles in Baidu academic
[Li Shen]'s Articles
[Gang Sun]'s Articles
[Shuhui Wang]'s Articles
Bing Scholar
Similar articles in Bing Scholar
[Li Shen]'s Articles
[Gang Sun]'s Articles
[Shuhui Wang]'s Articles
Terms of Use
No data!
Social Bookmark/Share
All comments (0)
No comment.
 

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