2026· IEEE Geoscience and Remote Sensing Letters· Vol 23, pp. 6019805-6019805· 0 citations· 19 references
TL;DR
ConceptSeg is presented, a text-guided multimodal segmentation framework that enables zero-shot segmentation of linguistically described geospatial objects in remote sensing imagery, supporting concept-driven segmentation for complex geospatial reasoning.
Abstract
The existing remote sensing image segmentation methods rely on predefined category labels, which are often insufficient to capture the complex spatial semantics inherent in geospatial concepts, such as flood inundation zones, landslide bodies, and industrial complexes. This letter presents ConceptSeg, a text-guided multimodal segmentation framework that enables zero-shot segmentation of linguistically described geospatial objects in remote sensing imagery. ConceptSeg employs a decoupled architecture comprising a multiscale image encoder with 2-D rotary position embedding (2D-RoPE), a unified multimodal prompt encoder with adaptive gated fusion, and a compact two-way cross-attention decoder, bridging natural-language concept descriptions with pixel-level predictions through region of interest (ROI)-guided feature extraction and contrastive alignment. With only $\approx $ 35 M trainable parameters atop frozen encoders, it stays markedly lighter than recent multimodal large-language-model baselines. Experiments on multiple benchmarks show up to +0.09 mIoU improvement over prior cascaded reasoning baselines out-of-domain, a smaller margin over concurrent open-vocabulary methods that is significant only with an external box prior, and consistent gIoU/cIoU gains in-domain, supporting concept-driven segmentation for complex geospatial reasoning.
This paper establishes the first cross-domain RRSIS benchmark, designated as the Vaihingen-Potsdam Referring (VPRef) dataset, and develops a tailored parameter-efficient domain adaptation baseline anchored on the Segment Anything Model (SAM3) via Low-Rank Adaptation (LoRA).
Quan-Wei Liu, Tao Huang, Jia-Qi Yang et al.· arXiv.org· 0 citations
DLPANet is proposed, a novel dual-level prototype alignment network centered on Prototype-Guided Spatial Attention, enabling simultaneous modeling of scene context and fine-grained details and demonstrates that the decoupled dual cross-attention mechanism provides superior prototype-query alignment compared to prior gl...
Mustafa Alawadi, M. Fateh· Jordanian Journal of Compute...· 0 citations
Earth observation image segmentation is a central geoinformatics task, enabling precise land cover mapping, infrastructure monitoring, and environmental change detection from satellite and aerial imagery. However, existing remote sensing segmentation models are typically trained for fixed class taxonomies, lack cross...
Ling Shi, Hang Li, Chang-Yun Shi et al.· Frontiers in Earth Science· 0 citations
Despite the economic advantages of weakly supervised semantic segmentation (WSSS) in remote sensing imagery (RSI), existing VLM- and VFM-based approaches still struggle with domain-specific semantic ambiguities and geometric discontinuities. To address these challenges, we propose GeoSeC, the Geometric-Semantic Collabo...
Xiang-Rong Zhang, Jian-Xun Lai, Guan-Chun Wang et al.· IEEE Transactions on Image P...· 0 citations
This work proposes M2-DINO, a parameter-efficient multimodal adaptation framework for remote sensing semantic segmentation, where topology-oriented terminology refers to architectural sensitivity to topology-relevant structures, such as thin-object continuity and object boundaries, rather than explicit optimization of...
Zi-Fei Luo, Yu-Bin He, Zhi-Yong Li et al.· IEEE Journal of Selected Top...· 0 citations
Domain-generalized semantic segmentation (DGSS) is critical for remote sensing and Earth observation imagery, where models trained on annotated satellite or unmanned aerial vehicle (UAV) imagery from a source region often suffer substantial performance degradation when deployed to unseen sensors, spatial resolutions, s...
Siyu Chen, Hui-Lin Xu, Yong-Le Fu et al.· IEEE Transactions on Geoscie...· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.