{"ID":2827448,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2512.16294","arxiv_id":"2512.16294","title":"MARC: Multi-Label Adaptive Retrieval Contrastive Loss for Remote Sensing Images","abstract":"Semantic overlap among land-cover categories, highly imbalanced label distributions, and complex inter-class co-occurrence patterns constitute significant challenges for multi-label remote-sensing image retrieval. In this article, Multi-Label Adaptive Contrastive Learning (MACL) is introduced as an extension of contrastive learning to address them. It integrates label-aware sampling, frequency-sensitive weighting, and dynamic-temperature scaling to achieve balanced representation learning across both common and rare categories. Extensive experiments on three benchmark datasets (DLRSD, ML-AID, and WHDLD), show that MACL consistently outperforms contrastive-loss based baselines, effectively mitigating semantic imbalance and delivering more reliable retrieval performance in large-scale remote-sensing archives. Code, pretrained models, and evaluation scripts will be released at https://github.com/Amna-128/MARC upon acceptance.","short_abstract":"Semantic overlap among land-cover categories, highly imbalanced label distributions, and complex inter-class co-occurrence patterns constitute significant challenges for multi-label remote-sensing image retrieval. In this article, Multi-Label Adaptive Contrastive Learning (MACL) is introduced as an extension of contras...","url_abs":"https://arxiv.org/abs/2512.16294","url_pdf":"https://arxiv.org/pdf/2512.16294v2","authors":"[\"Amna Amir\",\"Erchan Aptoula\"]","published":"2025-12-18T08:29:27Z","proceeding":"cs.CV","tasks":"[\"cs.CV\"]","methods":"[]","has_code":false,"code_links":[{"ID":605808,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_id":2827448,"paper_url":"https://arxiv.org/abs/2512.16294","paper_title":"MARC: Multi-Label Adaptive Retrieval Contrastive Loss for Remote Sensing Images","repo_url":"https://github.com/Amna-128/MARC","is_official":false,"mentioned_in_paper":false,"mentioned_in_github":true,"github_stars":0}]}