Research indexJournal article
Deep Representation Learning with Target Coding
Yang, Luo, Loy and 2 others
Proceedings of the AAAI Conference on Artificial Intelligence4 Mar 2015Open access
NobleIDark:/48914/w1/20260523/8A3487E5DOI10.1609/aaai.v29i1.9796
Deep Representation Learning with Target Coding
Yang, Luo, Loy and 2 others · Proceedings of the AAAI Conference on Artificial Intelligence · 2015
NobleIDark:/48914/w1/20260523/8A3487E5DOI10.1609/aaai.v29i1.9796
Abstract
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 acode with error correcting capability is more capable of encouraging discriminative features, in comparison tothe 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.