Large-Margin Softmax Loss for Convolutional Neural Networks

ICML, pp. 507-516, 2012.

Cited by: 492|Bibtex|Views94
EI
Other Links: dblp.uni-trier.de|academic.microsoft.com|arxiv.org

Abstract:

Cross-entropy loss together with softmax is arguably one of the most common used supervision components in convolutional neural networks (CNNs). Despite its simplicity, popularity and excellent performance, the component does not explicitly encourage discriminative learning of features. In this paper, we propose a generalized large-margin...More

Code:

Data:

Full Text
Your rating :
0

 

Tags
Comments