{"ID":2840228,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2511.14901","arxiv_id":"2511.14901","title":"FarSLIP: Discovering Effective CLIP Adaptation for Fine-Grained Remote Sensing Understanding","abstract":"As CLIP's global alignment limits its ability to capture fine-grained details, recent efforts have focused on enhancing its region-text alignment. However, current remote sensing (RS)-specific CLIP variants still inherit this limited spatial awareness. We identify two key limitations behind this: (1) current RS image-text datasets generate global captions from object-level labels, leaving the original object-level supervision underutilized; (2) despite the success of region-text alignment methods in general domain, their direct application to RS data often leads to performance degradation. To address these, we construct the first multi-granularity RS image-text dataset, MGRS-200k, featuring rich object-level textual supervision for RS region-category alignment. We further investigate existing fine-grained CLIP tuning strategies and find that current explicit region-text alignment methods, whether in a direct or indirect way, underperform due to severe degradation of CLIP's semantic coherence. Building on these, we propose FarSLIP, a Fine-grained Aligned RS Language-Image Pretraining framework. Rather than the commonly used patch-to-CLS self-distillation, FarSLIP employs patch-to-patch distillation to align local and global visual cues, which improves feature discriminability while preserving semantic coherence. Additionally, to effectively utilize region-text supervision, it employs simple CLS token-based region-category alignment rather than explicit patch-level alignment, further enhancing spatial awareness. FarSLIP features improved fine-grained vision-language alignment in RS domain and sets a new state of the art not only on RS open-vocabulary semantic segmentation, but also on image-level tasks such as zero-shot classification and image-text retrieval. Our dataset, code, and models are available at https://github.com/NJU-LHRS/FarSLIP.","short_abstract":"As CLIP's global alignment limits its ability to capture fine-grained details, recent efforts have focused on enhancing its region-text alignment. However, current remote sensing (RS)-specific CLIP variants still inherit this limited spatial awareness. We identify two key limitations behind this: (1) current RS image-t...","url_abs":"https://arxiv.org/abs/2511.14901","url_pdf":"https://arxiv.org/pdf/2511.14901v1","authors":"[\"Zhenshi Li\",\"Weikang Yu\",\"Dilxat Muhtar\",\"Xueliang Zhang\",\"Pengfeng Xiao\",\"Pedram Ghamisi\",\"Xiao Xiang Zhu\"]","published":"2025-11-18T20:39:15Z","proceeding":"cs.CV","tasks":"[\"cs.CV\"]","methods":"[]","has_code":false,"code_links":[{"ID":606952,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_id":2840228,"paper_url":"https://arxiv.org/abs/2511.14901","paper_title":"FarSLIP: Discovering Effective CLIP Adaptation for Fine-Grained Remote Sensing Understanding","repo_url":"https://github.com/NJU-LHRS/FarSLIP","is_official":false,"mentioned_in_paper":false,"mentioned_in_github":true,"github_stars":0}]}