Papers › Center Contrastive Loss for Metric Learning

Center Contrastive Loss for Metric Learning

1 Aug 2023arXiv:2308.00458archive 2025-07-28

Bolun Cai, Pengfei Xiong, Shangxuan Tian

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.

PaperPDF

Code

No code repository is listed for this paper in the archive or in Syntology's graph.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

Contrastive LearningMetric Learning

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Metric Learning CARS196 CCL (ResNet-50) R@1 91.02 #7 of 36 Archive leaderboard report
Metric Learning CUB-200-2011 CCL (ResNet-50) R@1 73.45 #5 of 30 Archive leaderboard report
Metric Learning In-Shop CCL (ResNet-50) R@1 92.31 #6 of 15 Archive leaderboard report
Metric Learning Stanford Online Products CCL (ResNet-50) R@1 83.10 #10 of 33 Archive leaderboard report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections