Share your thoughts, 1 month free Claude Pro on usSee more
WorkDL logo mark

Exploring Efficient Open-Vocabulary Segmentation in the Remote Sensing

About

Open-Vocabulary Remote Sensing Image Segmentation (OVRSIS), an emerging task that adapts Open-Vocabulary Segmentation (OVS) to the remote sensing (RS) domain, remains underexplored due to the absence of a unified evaluation benchmark and the domain gap between natural and RS images. To bridge these gaps, we first establish a standardized OVRSIS benchmark (\textbf{OVRSISBench}) based on widely-used RS segmentation datasets, enabling consistent evaluation across methods. Using this benchmark, we comprehensively evaluate several representative OVS/OVRSIS models and reveal their limitations when directly applied to remote sensing scenarios. Building on these insights, we propose \textbf{RSKT-Seg}, a novel open-vocabulary segmentation framework tailored for remote sensing. RSKT-Seg integrates three key components: (1) a Multi-Directional Cost Map Aggregation (RS-CMA) module that captures rotation-invariant visual cues by computing vision-language cosine similarities across multiple directions; (2) an Efficient Cost Map Fusion (RS-Fusion) transformer, which jointly models spatial and semantic dependencies with a lightweight dimensionality reduction strategy; and (3) a Remote Sensing Knowledge Transfer (RS-Transfer) module that injects pre-trained knowledge and facilitates domain adaptation via enhanced upsampling. Extensive experiments on the benchmark show that RSKT-Seg consistently outperforms strong OVS baselines by +3.8 mIoU and +5.9 mACC, while achieving 2x faster inference through efficient aggregation. Our code is \href{https://github.com/LiBingyu01/RSKT-Seg}{\textcolor{blue}{here}}.

Bingyu Li, Haocheng Dong, Da Zhang, Zhiyuan Zhao, Junyu Gao, Xuelong Li• 2025

Related benchmarks

TaskDatasetResultRank
Semantic segmentationLoveDA
mIoU33.2
166
Semantic segmentationVaihingen
mIoU42.7
140
Semantic segmentationiSAID
mIoU93.96
122
Semantic segmentationLoveDA
mIoU40.71
92
Semantic segmentationPotsdam
mIoU38.4
81
Semantic segmentationVDD
mIoU41.22
76
Semantic segmentationUAVid
mIoU28.14
68
Semantic segmentationUDD5
mIoU45.73
63
Semantic segmentationDLRSD
mIoU91.58
32
Semantic segmentationMean over 8 Remote Sensing Datasets
Mean mIoU46.18
32
Showing 10 of 20 rows

Other info

Follow for update