Transfer classification for distinct manifestations with shared information
Qi, Lu1; Yin, Peijie2; Huang, Xiayuan2; Chen, Ken3; Qiao, Hong1; Qi, L
2016
Conference Name12th World Congress on Intelligent Control and Automation (WCICA)
Source PublicationPROCEEDINGS OF THE 2016 12TH WORLD CONGRESS ON INTELLIGENT CONTROL AND AUTOMATION (WCICA)
Conference DateJUN 12-15, 2016
Conference PlaceGuilin, PEOPLES R CHINA
AbstractAn object often has many distinct manifestations in computer vision, which brings a great challenge to utilizing more comprehensive information. Inspired by some biological researches about edge sensitivity and global structure priority, our key insight is to establish unified transfer classification network withshared contour information. Combining two convolutional networks with three cascaded filters, we build a unified kernel SVM classifier based on shared contour features. Two convolutional networks are usedfor acquiring the contour information of objects exactly. Obtained by three cascaded filters, sharededge features are used by a unified kernels SVM classifier. Our transfer classification network(TCN) is trained and tested with distinct manifestations including real photos(imagenet dataset or cifar-10 dataset) and cartoon abstracts. The model is able to extract robust contour features and achieve considerable transfer recognition accuracy(40% relative improvement to some popular convolutional models).
KeywordVisual-cortex
Indexed ByEI
Document Type会议论文
Identifierhttp://ir.ia.ac.cn/handle/173211/12827
Collection复杂系统管理与控制国家重点实验室_机器人理论与应用
Corresponding AuthorQi, L
Affiliation1.Institution of Automation, Chinese Academy of Sciences
2.Academy of Mathematics and Systems Sciences, Chinese Academy of Sciences
3.Tsinghua University
Recommended Citation
GB/T 7714
Qi, Lu,Yin, Peijie,Huang, Xiayuan,et al. Transfer classification for distinct manifestations with shared information[C],2016.
Files in This Item: Download All
File Name/Size DocType Version Access License
Transfer classificat(1351KB)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
[Qi, Lu]'s Articles
[Yin, Peijie]'s Articles
[Huang, Xiayuan]'s Articles
Baidu academic
Similar articles in Baidu academic
[Qi, Lu]'s Articles
[Yin, Peijie]'s Articles
[Huang, Xiayuan]'s Articles
Bing Scholar
Similar articles in Bing Scholar
[Qi, Lu]'s Articles
[Yin, Peijie]'s Articles
[Huang, Xiayuan]'s Articles
Terms of Use
No data!
Social Bookmark/Share
File name: Transfer classification for distinct manifestations.pdf
Format: Adobe PDF
All comments (0)
No comment.
 

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