Center Contrastive Loss for Metric Learning

TL;DR

This paper introduces Center Contrastive Loss, a novel metric learning approach that uses class centers to improve embedding discrimination and convergence without complex sampling, achieving state-of-the-art results.

Contribution

The paper proposes Center Contrastive Loss, which maintains a class-wise center bank for effective contrastive learning without sample mining, enhancing convergence and discriminative power.

Findings

Achieves state-of-the-art performance on benchmark datasets.

Faster convergence compared to traditional contrastive methods.

Effectively balances intra-class and inter-class variations.

Abstract

Contrastive learning is a major studied topic in metric learning. However, sampling effective contrastive pairs remains a challenge due to factors such as limited batch size, imbalanced data distribution, and the risk of overfitting. In this paper, we propose a novel metric learning function called Center Contrastive Loss, which maintains a class-wise center bank and compares the category centers with the query data points using a contrastive loss. The center bank is updated in real-time to boost model convergence without the need for well-designed sample mining. The category centers are well-optimized classification proxies to re-balance the supervisory signal of each class. Furthermore, the proposed loss combines the advantages of both contrastive and classification methods by reducing intra-class variations and enhancing inter-class differences to improve the discriminative power of embeddings. Our experimental results, as shown in Figure 1, demonstrate that a standard network (ResNet50) trained with our loss achieves state-of-the-art performance and faster convergence.