Contrastive-center loss for deep neural networks
This work addresses the need for more effective supervision in deep learning for computer vision tasks, offering an incremental improvement over standard softmax-based methods.
The paper tackles the problem of enhancing feature discriminability in deep neural networks by introducing a novel auxiliary supervision signal called contrastive-center loss, which improves intra-class compactness and inter-class separability, leading to better performance on image classification and face recognition datasets.
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 contrastivecenter 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.