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.

翻译：对比学习是度量学习中的一个重要研究课题。然而，由于批次大小有限、数据分布不平衡以及过拟合风险等因素，有效采样对比对仍然是一个挑战。在本文中，我们提出了一种新颖的度量学习函数，即中心对比损失（Center Contrastive Loss），该函数维护了一个类别级别的中心库，并利用对比损失将类别中心与查询数据点进行比较。中心库实时更新以促进模型收敛，无需精心设计的样本挖掘策略。类别中心作为优化良好的分类代理，能够重新平衡每个类别的监督信号。此外，所提出的损失函数结合了对比方法和分类方法的优势，通过减少类内差异并增强类间差异来提高嵌入的判别能力。如图1所示，我们的实验结果表明，使用所提损失函数训练的标准网络（ResNet50）达到了最先进的性能，并实现了更快的收敛速度。