{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/center-contrastive-loss-for-metric-learning","title":"Center Contrastive Loss for Metric Learning","arxiv_id":"2308.00458","date":"2023-08-01","proceeding":null,"authors":["Bolun Cai","Pengfei Xiong","Shangxuan Tian"],"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.","url_abs":"https://arxiv.org/abs/2308.00458v1","url_pdf":"https://arxiv.org/pdf/2308.00458v1.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[],"tasks":[{"task_slug":"contrastive-learning","task_name":"Contrastive Learning"},{"task_slug":"metric-learning","task_name":"Metric Learning"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/metric-learning-on-cars196","task":"Metric Learning","dataset":"CARS196","model":"CCL (ResNet-50)","rank_in_archive_order":7,"of":36,"metrics":{"R@1":"91.02"},"uses_additional_data":false},{"leaderboard":"/sota/metric-learning-on-cub-200-2011","task":"Metric Learning","dataset":"CUB-200-2011","model":"CCL (ResNet-50)","rank_in_archive_order":5,"of":30,"metrics":{"R@1":"73.45"},"uses_additional_data":false},{"leaderboard":"/sota/metric-learning-on-in-shop-1","task":"Metric Learning","dataset":"In-Shop","model":"CCL (ResNet-50)","rank_in_archive_order":6,"of":15,"metrics":{"R@1":"92.31"},"uses_additional_data":false},{"leaderboard":"/sota/metric-learning-on-stanford-online-products-1","task":"Metric Learning","dataset":"Stanford Online Products","model":"CCL (ResNet-50)","rank_in_archive_order":10,"of":33,"metrics":{"R@1":"83.10"},"uses_additional_data":false}],"syntology":{"syntology_url":null,"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}