Documents
Poster
CONTRASTIVE-CENTER LOSS FOR DEEP NEURAL NETWORKS
- Citation Author(s):
- Submitted by:
- Ce Qi
- Last updated:
- 13 September 2017 - 10:46pm
- Document Type:
- Poster
- Document Year:
- 2017
- Event:
- Presenters:
- Ce Qi
- Paper Code:
- 1592
- Categories:
- Log in to post comments
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.