# FarSLIP: Discovering Effective CLIP Adaptation for Fine-Grained Remote Sensing Understanding arXiv: https://arxiv.org/abs/2511.14901 ยท HTML: https://mlsanity.com/paper/2511.14901/ ## Key facts - Cited by 1 papers in the map (data through 14 Oct 2026). - Builds on 59 of its 75 references that are in the map. - First posted on arXiv 18 Nov 2025. ## Builds on (most cited first, 30 of 59) - [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021) - [DINOv2: Learning Robust Visual Features without Supervision](https://mlsanity.com/paper/2304.07193/) (2023) - [Mask R-CNN](https://mlsanity.com/paper/1703.06870/) (2017) - [Supervised Contrastive Learning](https://mlsanity.com/paper/2004.11362/) (2020) - [InternVL3: Exploring Advanced Training and Test-Time Recipes for Open-Source Multimodal Models](https://mlsanity.com/paper/2504.10479/) (2025) - [EuroSAT: A Novel Dataset and Deep Learning Benchmark for Land Use and Land Cover Classification](https://mlsanity.com/paper/1709.00029/) (2017) - [SigLIP 2: Multilingual Vision-Language Encoders with Improved Semantic Understanding, Localization, and Dense Features](https://mlsanity.com/paper/2502.14786/) (2025) - [Remote Sensing Image Scene Classification: Benchmark and State of the Art](https://mlsanity.com/paper/1703.00121/) (2017) - [Fine-Tuning can Distort Pretrained Features and Underperform Out-of-Distribution](https://mlsanity.com/paper/2202.10054/) (2022) - [DOTA: A Large-scale Dataset for Object Detection in Aerial Images](https://mlsanity.com/paper/1711.10398/) (2017) - [RegionCLIP: Region-based Language-Image Pretraining](https://mlsanity.com/paper/2112.09106/) (2021) - [Extract Free Dense Labels from CLIP](https://mlsanity.com/paper/2112.01071/) (2021) - [RemoteCLIP: A Vision Language Foundation Model for Remote Sensing](https://mlsanity.com/paper/2306.11029/) (2023) - [AID: A Benchmark Dataset for Performance Evaluation of Aerial Scene Classification](https://mlsanity.com/paper/1608.05167/) (2016) - [Object Detection in Optical Remote Sensing Images: A Survey and A New Benchmark](https://mlsanity.com/paper/1909.00133/) (2019) - [Functional Map of the World](https://mlsanity.com/paper/1711.07846/) (2017) - [Long-CLIP: Unlocking the Long-Text Capability of CLIP](https://mlsanity.com/paper/2403.15378/) (2024) - [LoveDA: A Remote Sensing Land-Cover Dataset for Domain Adaptive Semantic Segmentation](https://mlsanity.com/paper/2110.08733/) (2021) - [Exploring Models and Data for Remote Sensing Image Caption Generation](https://mlsanity.com/paper/1712.07835/) (2017) - [iSAID: A Large-scale Dataset for Instance Segmentation in Aerial Images](https://mlsanity.com/paper/1905.12886/) (2019) - [StableRep: Synthetic Images from Text-to-Image Models Make Strong Visual Representation Learners](https://mlsanity.com/paper/2306.00984/) (2023) - [SCLIP: Rethinking Self-Attention for Dense Vision-Language Inference](https://mlsanity.com/paper/2312.01597/) (2023) - [Drone-based Object Counting by Spatially Regularized Regional Proposal Network](https://mlsanity.com/paper/1707.05972/) (2017) - [RS5M and GeoRSCLIP: A Large Scale Vision-Language Dataset and A Large Vision-Language Model for Remote Sensing](https://mlsanity.com/paper/2306.11300/) (2023) - [Finetune like you pretrain: Improved finetuning of zero-shot vision models](https://mlsanity.com/paper/2212.00638/) (2022) - [xView: Objects in Context in Overhead Imagery](https://mlsanity.com/paper/1802.07856/) (2018) - [FAIR1M: A Benchmark Dataset for Fine-grained Object Recognition in High-Resolution Remote Sensing Imagery](https://mlsanity.com/paper/2103.05569/) (2021) - [LHRS-Bot: Empowering Remote Sensing with VGI-Enhanced Large Multimodal Language Model](https://mlsanity.com/paper/2402.02544/) (2024) - [SkyScript: A Large and Semantically Diverse Vision-Language Dataset for Remote Sensing](https://mlsanity.com/paper/2312.12856/) (2023) - [CLIPSelf: Vision Transformer Distills Itself for Open-Vocabulary Dense Prediction](https://mlsanity.com/paper/2310.01403/) (2023) ## Built on by (most cited first, 1 of 1) - [EarthEmbeddingExplorer: A Web Application for Cross-Modal Retrieval of Global Satellite Images](https://mlsanity.com/paper/2603.29441/) (2026) ## Abstract (arXiv) 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.