UM
Multi-Task CNN Model for Attribute Prediction
Abdulnabi A.H.; Wang G.; Lu J.; Jia K.
2015
Source PublicationIEEE Transactions on Multimedia
ISSN15209210
Volume17Issue:11Pages:1949
AbstractThis paper proposes a joint multi-task learning algorithm to better predict attributes in images using deep convolutional neural networks (CNN). We consider learning binary semantic attributes through a multi-task CNN model, where each CNN will predict one binary attribute. The multi-task learning allows CNN models to simultaneously share visual knowledge among different attribute categories. Each CNN will generate attribute-specific feature representations, and then we apply multi-task learning on the features to predict their attributes. In our multi-task framework, we propose a method to decompose the overall model's parameters into a latent task matrix and combination matrix. Furthermore, under-sampled classifiers can leverage shared statistics from other classifiers to improve their performance. Natural grouping of attributes is applied such that attributes in the same group are encouraged to share more knowledge. Meanwhile, attributes in different groups will generally compete with each other, and consequently share less knowledge. We show the effectiveness of our method on two popular attribute datasets. © 2015 IEEE.
KeywordDeep CNN latent tasks matrix multi-task learning semantic attributes
DOI10.1109/TMM.2015.2477680
URLView the original
Language英语
The Source to ArticleScopus
Fulltext Access
Citation statistics
Cited Times [WOS]:75   [WOS Record]     [Related Records in WOS]
Document TypeJournal article
CollectionUniversity of Macau
Recommended Citation
GB/T 7714
Abdulnabi A.H.,Wang G.,Lu J.,et al. Multi-Task CNN Model for Attribute Prediction[J]. IEEE Transactions on Multimedia,2015,17(11):1949.
APA Abdulnabi A.H.,Wang G.,Lu J.,&Jia K..(2015).Multi-Task CNN Model for Attribute Prediction.IEEE Transactions on Multimedia,17(11),1949.
MLA Abdulnabi A.H.,et al."Multi-Task CNN Model for Attribute Prediction".IEEE Transactions on Multimedia 17.11(2015):1949.
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
[Abdulnabi A.H.]'s Articles
[Wang G.]'s Articles
[Lu J.]'s Articles
Baidu academic
Similar articles in Baidu academic
[Abdulnabi A.H.]'s Articles
[Wang G.]'s Articles
[Lu J.]'s Articles
Bing Scholar
Similar articles in Bing Scholar
[Abdulnabi A.H.]'s Articles
[Wang G.]'s Articles
[Lu J.]'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.