Papers › Enhancing Remote Sensing Vision-Language Models for Zero-Shot Scene Classification

Enhancing Remote Sensing Vision-Language Models for Zero-Shot Scene Classification

1 Sep 2024arXiv:2409.00698archive 2025-07-28

Karim El Khoury, Maxime Zanella, Benoît Gérin, Tiffanie Godelaine, Benoît Macq, Saïd Mahmoudi, Christophe De Vleeschouwer, Ismail Ben Ayed

Vision-Language Models for remote sensing have shown promising uses thanks to their extensive pretraining. However, their conventional usage in zero-shot scene classification methods still involves dividing large images into patches and making independent predictions, i.e., inductive inference, thereby limiting their effectiveness by ignoring valuable contextual information. Our approach tackles this issue by utilizing initial predictions based on text prompting and patch affinity relationships from the image encoder to enhance zero-shot capabilities through transductive inference, all without the need for supervision and at a minor computational cost. Experiments on 10 remote sensing datasets with state-of-the-art Vision-Language Models demonstrate significant accuracy improvements over inductive zero-shot classification. Our source code is publicly available on Github: https://github.com/elkhouryk/RS-TransCLIP

PaperPDFCode

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

Code

elkhouryk/rs-transclip officialmentioned in papermentioned on GitHubpytorch 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

Scene ClassificationTransductive Zero-Shot ClassificationZero-Shot Learning

1 archive task tag without a task page not shown.

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Transductive Zero-Shot Classification AID RS-TransCLIP Accuracy 92.7 #1 of 1 Archive leaderboard report
Transductive Zero-Shot Classification EuroSAT RS-TransCLIP Accuracy 91.2 #1 of 2 Archive leaderboard report
Transductive Zero-Shot Classification MLRSNet RS-TransCLIP Accuracy 78.1 #1 of 1 Archive leaderboard report
Transductive Zero-Shot Classification OPTIMAL31 RS-TransCLIP Accuracy 94.5 #1 of 1 Archive leaderboard report
Transductive Zero-Shot Classification PatternNet RS-TransCLIP Accuracy 96.2 #1 of 1 Archive leaderboard report
Transductive Zero-Shot Classification RESISC45 RS-TransCLIP Accuracy 88 #1 of 1 Archive leaderboard report
Transductive Zero-Shot Classification RSC11 RS-TransCLIP Accuracy 88.1 #1 of 1 Archive leaderboard report
Transductive Zero-Shot Classification RSICB128 RS-TransCLIP Accuracy 54.8 #1 of 1 Archive leaderboard report
Transductive Zero-Shot Classification RSICB256 RS-TransCLIP Accuracy 72.8 #1 of 1 Archive leaderboard report
Transductive Zero-Shot Classification WHURS19 RS-TransCLIP Accuracy 99.7 #1 of 1 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.

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