论文浏览

【论文题目】CONTRASTIVE-CENTER LOSS FOR DEEP NEURAL NETWORKS

【作    者】Ce Qi, Fei Su        点击下载PDF全文

【关 键 字】Class center, Auxiliary loss, Deep convolutional neural networks, Image classification and face recognition

【发表刊物/会议】
    2017 IEEE International Conference on Image Processing(ICIP)

【摘    要】
     The deep convolutional neural network(CNN) has significantly raised the performance of image classification and face recognition. Softmax is usually used as supervision, but it only penalizes the classification loss. In this paper, we propose a novel auxiliary supervision signal called contrastive-center loss, which can further enhance the discriminative power of the features, for it learns a class center for each class. The proposed contrastive-center loss simultaneously considers intra-class compactness and inter-class separability, by penalizing the contrastive values between: (1)the distances of training samples to their corresponding class centers, and (2)the sum of the distances of training samples to their non-corresponding class centers. Experiments on different datasets demonstrate the effectiveness of contrastive-center loss.

【发 表 年】2017

【发 表 月】10

【类    别】模式识别


Tel: 086-010-62283118 邮编:100876
地址:北京市海淀区西土城路10号北京邮电大学教二楼多媒体中心
北京市海淀区西土城路十号113#信箱
版权所有:北京邮电大学多媒体通信与模式识别研究室 京ICP证14002347号