GeoSeg: Training-Free Reasoning-Driven Segmentation in Remote Sensing Imagery
Recent advances in MLLMs are reframing segmentation from fixed-category prediction to instruction-grounded localization. While reasoning based segmentation has progressed rapidly in natural scenes, remote sensing lacks a generalizable solution due to the prohibitive cost of reasoning-oriented data and domain-specific challenges like overhead viewpoints. We present GeoSeg, a zero-shot, training-free framework that bypasses the supervision bottleneck for reasoning-driven remote sensing segmentation. GeoSeg couples MLLM reasoning with precise localization via: (i) bias-aware coordinate refinement to correct systematic grounding shifts and (ii) a dual-route prompting mechanism to fuse semantic intent with fine-grained spatial cues. We also introduce GeoSeg-Bench, a diagnostic benchmark of 810 image--query pairs with hierarchical difficulty levels. Experiments show that GeoSeg consistently outperforms all baselines, with extensive ablations confirming the effectiveness and necessity of each component.
Code (0)
등록된 구현이 없습니다.
Similar Papers 제목 키워드 기반
UniGeoSeg: Towards Unified Open-World Segmentation for Geospatial Scenes
Instruction-driven segmentation in remote sensing generates masks from guidance, offering great potential for accessible and generalizable applications. However, existing methods suffer from fragmented task formulations …
Zero-shot GeneralizationMulti-Task LearningGeoseg: A Computer Vision Package for Automatic Building Segmentation and Outline Extraction
Recently, deep learning algorithms, especially fully convolutional network based methods, are becoming very popular in the field of remote sensing. However, these methods are implemented and evaluated through various dat…
Computational EfficiencyDeep LearningPrimitive Geometry Segment Pre-training for 3D Medical Image Segmentation
The construction of 3D medical image datasets presents several issues, including requiring significant financial costs in data collection and specialized expertise for annotation, as well as strict privacy concerns for p…
Image SegmentationMedical Image SegmentationSegmentationSelf-Supervised Learning+1GeoSegNet: Point Cloud Semantic Segmentation via Geometric Encoder-Decoder Modeling
Semantic segmentation of point clouds, aiming to assign each point a semantic category, is critical to 3D scene understanding.Despite of significant advances in recent years, most of existing methods still suffer from ei…
DecoderObjectSegmentationSemantic SegmentationUNetFormer: A UNet-like Transformer for Efficient Semantic Segmentation of Remote Sensing Urban Scene Imagery
Semantic segmentation of remotely sensed urban scene images is required in a wide range of practical applications, such as land cover mapping, urban change detection, environmental protection, and economic assessment.Dri…
Change DetectionDecoderGPUimage-classification+6