Papers › RemoteCLIP: A Vision Language Foundation Model for Remote Sensing

RemoteCLIP: A Vision Language Foundation Model for Remote Sensing

19 Jun 2023arXiv:2306.11029archive 2025-07-28

Fan Liu, Delong Chen, Zhangqingyun Guan, Xiaocong Zhou, Jiale Zhu, Qiaolin Ye, Liyong Fu, Jun Zhou

General-purpose foundation models have led to recent breakthroughs in artificial intelligence. In remote sensing, self-supervised learning (SSL) and Masked Image Modeling (MIM) have been adopted to build foundation models. However, these models primarily learn low-level features and require annotated data for fine-tuning. Moreover, they are inapplicable for retrieval and zero-shot applications due to the lack of language understanding. To address these limitations, we propose RemoteCLIP, the first vision-language foundation model for remote sensing that aims to learn robust visual features with rich semantics and aligned text embeddings for seamless downstream application. To address the scarcity of pre-training data, we leverage data scaling which converts heterogeneous annotations into a unified image-caption data format based on Box-to-Caption (B2C) and Mask-to-Box (M2B) conversion. By further incorporating UAV imagery, we produce a 12 × larger pretraining dataset than the combination of all available datasets. RemoteCLIP can be applied to a variety of downstream tasks, including zero-shot image classification, linear probing, k-NN classification, few-shot classification, image-text retrieval, and object counting in remote sensing images. Evaluation on 16 datasets, including a newly introduced RemoteCount benchmark to test the object counting ability, shows that RemoteCLIP consistently outperforms baseline foundation models across different model scales. Impressively, RemoteCLIP beats the state-of-the-art method by 9.14% mean recall on the RSITMD dataset and 8.92% on the RSICD dataset. For zero-shot classification, our RemoteCLIP outperforms the CLIP baseline by up to 6.39% average accuracy on 12 downstream datasets. Project website: https://github.com/ChenDelong1999/RemoteCLIP

PaperPDFCode

In Syntology View this paper on Syntology, its page in Syntology's graph. That page lists the repositories linked to the paper, the abstract and the calls for agents.

Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

For agents, on Syntology's MCP service (how to connect):

Code

chendelong1999/remoteclip officialmentioned in papermentioned on GitHubpytorchApache-2.0Syntology: not harvested report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

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

Tasks

ClassificationCross-Modal RetrievalImage ClassificationImage-text RetrievalObject CountingRetrievalSelf-Supervised LearningText RetrievalZero-Shot Image ClassificationZero-Shot Learningimage-classification

1 archive task tag without a task page not shown.

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Cross-Modal Retrieval RSICD RemoteCLIP Image-to-text R@1 18.39% #4 of 10 Archive leaderboard report
Cross-Modal Retrieval RSICD RemoteCLIP Mean Recall 36.35% #4 of 10 Archive leaderboard report
Cross-Modal Retrieval RSICD RemoteCLIP text-to-image R@1 14.73% #4 of 10 Archive leaderboard report
Cross-Modal Retrieval RSITMD RemoteCLIP Image-to-text R@1 28.76% #4 of 10 Archive leaderboard report
Cross-Modal Retrieval RSITMD RemoteCLIP Mean Recall 50.52% #4 of 10 Archive leaderboard report
Cross-Modal Retrieval RSITMD RemoteCLIP text-to-imageR@1 23.76% #4 of 10 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.

Methods

CLIPk-NN

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