CASIA OpenIR  > 智能感知与计算研究中心
Discriminative Learning of Latent Features for Zero-Shot Recognition
Li Y(李岩)1,2; Zhang JG(张俊格)1,2; Zhang JG(张建国)3; Huang KQ(黄凯奇)1,2,4
2018
Conference NameIEEE Conference on Computer Vision and Pattern Recognition
Pages7463-7471
Conference Date2018.06.18-2018.06.22
Conference PlaceSalt Lake City, USA
Abstract

Zero-shot learning (ZSL) aims to recognize unseen image categories by learning an embedding space between image and semantic representations. For years, among existing works, it has been the center task to learn the proper mapping matrices aligning the visual and semantic space, whilst the importance to learn discriminative representations for ZSL is ignored. In this work, we retrospect existing methods and demonstrate the necessity to learn discriminative representations for both visual and semantic instances of ZSL. We propose an end-to-end network that is capable of 1) automatically discovering discriminative regions by a zoom network; and 2) learning discriminative semantic representations in an augmented space introduced for both user-defined and latent attributes. Our proposed method is tested extensively on two challenging ZSL datasets, and the experiment results show that the proposed method significantly outperforms state-of-the-art methods.

Document Type会议论文
Identifierhttp://ir.ia.ac.cn/handle/173211/23344
Collection智能感知与计算研究中心
Corresponding AuthorHuang KQ(黄凯奇)
Affiliation1.中国科学院自动化研究所
2.University of Chinese Academy of Sciences
3.Computing, School of Science and Engineering, Univerisity of Dundee, UK
4.CAS Center for Excellence in Brain Science and Intelligence Technology
First Author AffilicationInstitute of Automation, Chinese Academy of Sciences
Corresponding Author AffilicationInstitute of Automation, Chinese Academy of Sciences
Recommended Citation
GB/T 7714
Li Y,Zhang JG,Zhang JG,et al. Discriminative Learning of Latent Features for Zero-Shot Recognition[C],2018:7463-7471.
Files in This Item: Download All
File Name/Size DocType Version Access License
CVPR-published.pdf(1604KB)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
[Li Y(李岩)]'s Articles
[Zhang JG(张俊格)]'s Articles
[Zhang JG(张建国)]'s Articles
Baidu academic
Similar articles in Baidu academic
[Li Y(李岩)]'s Articles
[Zhang JG(张俊格)]'s Articles
[Zhang JG(张建国)]'s Articles
Bing Scholar
Similar articles in Bing Scholar
[Li Y(李岩)]'s Articles
[Zhang JG(张俊格)]'s Articles
[Zhang JG(张建国)]'s Articles
Terms of Use
No data!
Social Bookmark/Share
File name: CVPR-published.pdf
Format: Adobe PDF
All comments (0)
No comment.
 

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