File Download
  Links for fulltext
     (May Require Subscription)
Supplementary

Conference Paper: Deep representation learning with target coding

TitleDeep representation learning with target coding
Authors
Yang, ShuoLuo, PingLoy, Chen ChangeShum, Kenneth W.Tang, Xiaoou
Issue Date2015
PublisherAssociation for the Advancement of Artificial Intelligence. The conference proceedings' web site is located at https://www.aaai.org/ocs/index.php/AAAI/AAAI15/index
Citation
Proceedings of the Twenty-Ninth AAAI Conference on Artificial Intelligence and the Twenty-Seventh Innovative Applications of Artificial Intelligence Conference, 2015, v. 5, p. 3848-3854 How to Cite?
Abstract© Copyright 2015, Association for the Advancement of Artificial Intelligence (www.aaai.org). All rights reserved. We consider the problem of learning deep representation when target labels are available. In this paper, we show that there exists intrinsic relationship between target coding and feature representation learning in deep networks. Specifically, we found that distributed binary code with error correcting capability is more capable of encouraging discriminative features, in comparison to the 1-of-K coding that is typically used in supervised deep learning. This new finding reveals additional benefit of using error-correcting code for deep model learning, apart from its well-known error correcting property. Extensive experiments are conducted on popular visual benchmark datasets.
Persistent Identifierhttp://hdl.handle.net/10722/273715

 

DC FieldValueLanguage
dc.contributor.authorYang, Shuo-
dc.contributor.authorLuo, Ping-
dc.contributor.authorLoy, Chen Change-
dc.contributor.authorShum, Kenneth W.-
dc.contributor.authorTang, Xiaoou-
dc.date.accessioned2019-08-12T09:56:27Z-
dc.date.available2019-08-12T09:56:27Z-
dc.date.issued2015-
dc.identifier.citationProceedings of the Twenty-Ninth AAAI Conference on Artificial Intelligence and the Twenty-Seventh Innovative Applications of Artificial Intelligence Conference, 2015, v. 5, p. 3848-3854-
dc.identifier.urihttp://hdl.handle.net/10722/273715-
dc.description.abstract© Copyright 2015, Association for the Advancement of Artificial Intelligence (www.aaai.org). All rights reserved. We consider the problem of learning deep representation when target labels are available. In this paper, we show that there exists intrinsic relationship between target coding and feature representation learning in deep networks. Specifically, we found that distributed binary code with error correcting capability is more capable of encouraging discriminative features, in comparison to the 1-of-K coding that is typically used in supervised deep learning. This new finding reveals additional benefit of using error-correcting code for deep model learning, apart from its well-known error correcting property. Extensive experiments are conducted on popular visual benchmark datasets.-
dc.languageeng-
dc.publisherAssociation for the Advancement of Artificial Intelligence. The conference proceedings' web site is located at https://www.aaai.org/ocs/index.php/AAAI/AAAI15/index-
dc.relation.ispartofProceedings of the National Conference on Artificial Intelligence-
dc.titleDeep representation learning with target coding-
dc.typeConference_Paper-
dc.description.naturelink_to_OA_fulltext-
dc.identifier.scopuseid_2-s2.0-84961226179-
dc.identifier.volume5-
dc.identifier.spage3848-
dc.identifier.epage3854-

Export via OAI-PMH Interface in XML Formats

OR

Export to Other Non-XML Formats