【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
2017 IEEE International Conference on Image Processing（ICIP）
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