Back to Search Start Over

More discriminative convolutional neural network with inter-class constraint for classification.

Authors :
Fei, Jianchao
Rui, Ting
Song, Xiaona
Zhou, You
Zhang, Sai
Source :
Computers & Electrical Engineering. May2018, Vol. 68, p484-489. 6p.
Publication Year :
2018

Abstract

Recently, convolutional neural network (CNN) has achieved impressive results in object classification tasks. Through various modifications and careful design of the inner structure of CNN, its performance has already become human-competitive, according to recent reports. To some extent, the testing accuracy depends largely on the decision boundaries produced by classifiers, which classify different objects into specific feature spaces. Hence, the relationships among samples in the feature space are critical. However, the softmax loss function that is used in most CNN models, does not directly contain the relationship information. In this paper, we propose a novel loss function, named inter-class constraint loss function, that maximizes the distance between different classes. Together with softmax loss, we can obtain larger inter-class distances and smaller intra-class distances in CNN, thus significantly improving the accuracy in classification. We achieve substantial improvements for the SVHN, CIFAR-10 and CIFAR-100 datasets using our proposed loss function. [ABSTRACT FROM AUTHOR]

Details

Language :
English
ISSN :
00457906
Volume :
68
Database :
Academic Search Index
Journal :
Computers & Electrical Engineering
Publication Type :
Academic Journal
Accession number :
129947607
Full Text :
https://doi.org/10.1016/j.compeleceng.2018.05.002