GeoSeg: Training-Free Reasoning-Driven Segmentation in Remote Sensing Imagery

• URL: http://arxiv.org/abs/2603.03983v1
• Date: Wed, 04 Mar 2026 12:24:16 GMT
• Title: GeoSeg: Training-Free Reasoning-Driven Segmentation in Remote Sensing Imagery
• Authors: Lifan Jiang, Yuhang Pei, oxi Wu, Yan Zhao, Tianrun Wu, Shulong Yu, Lihui Zhang, Deng Cai,
• Abstract summary: We present GeoSeg, a zero-shot, training-free framework that bypasses the supervision bottleneck for reasoning-driven remote sensing segmentation.<n>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.<n>Experiments show that GeoSeg consistently outperforms all baselines, with extensive ablations confirming the effectiveness and necessity of each component.
• Score: 12.65874706732698
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: 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.

Related papers

• RSGround-R1: Rethinking Remote Sensing Visual Grounding through Spatial Reasoning [61.84363374647606]
  Remote Sensing Visual Grounding (RSVG) aims to localize target objects in large-scale aerial imagery based on natural language descriptions.<n>These descriptions often rely heavily on positional cues, posing unique challenges for Multimodal Large Language Models (MLLMs) in spatial reasoning.<n>We propose a reasoning-guided, position-aware post-training framework, dubbed textbfRSGround-R1, to progressively enhance spatial understanding.
  arXiv  Detail & Related papers  (2026-01-29T12:35:57Z)
• SegEarth-R2: Towards Comprehensive Language-guided Segmentation for Remote Sensing Images [49.52402091341301]
  Current models can parse simple, single-target commands but fail when presented with complex geospatial scenarios.<n>We present LaSeRS, the first large-scale dataset built for comprehensive training and evaluation.<n>We also propose SegEarth-R2, an MLLM architecture designed for comprehensive language-guided segmentation in RS.
  arXiv  Detail & Related papers  (2025-12-23T03:10:17Z)
• Bridging Semantics and Geometry: A Decoupled LVLM-SAM Framework for Reasoning Segmentation in Remote Sensing [8.731693840957716]
  Think2Seg-RS is a framework that trains an LVLM prompter to control a frozen Segment Anything Model (SAM) via structured geometric prompts.<n>The framework achieves state-of-the-art performance on the EarthReason dataset.<n> compact segmenters outperform larger ones under semantic-level supervision, and that negative prompts are ineffective in heterogeneous aerial backgrounds.
  arXiv  Detail & Related papers  (2025-12-22T11:46:42Z)
• GeoZero: Incentivizing Reasoning from Scratch on Geospatial Scenes [84.52881742231152]
  Multimodal large language models (MLLMs) have undergone rapid development in advancing geospatial scene understanding.<n>Recent studies have sought to enhance the reasoning capabilities of remote sensing MLLMs, typically through cold-start training with elaborately curated chain-of-thought (CoT) data.<n>We propose GeoZero, a framework that enables MLLMs to perform geospatial reasoning without any predefined CoT supervision.
  arXiv  Detail & Related papers  (2025-11-27T17:28:09Z)
• Geo-R1: Improving Few-Shot Geospatial Referring Expression Understanding with Reinforcement Fine-Tuning [37.90271368636318]
  Referring expression understanding in remote sensing poses unique challenges.<n>We propose Geo-R1, a reasoning-centric reinforcement fine-tuning (RFT) paradigm for few-shot geospatial referring.
  arXiv  Detail & Related papers  (2025-09-26T07:01:12Z)
• Recognition through Reasoning: Reinforcing Image Geo-localization with Large Vision-Language Models [47.98900725310249]
  New pipeline constructs a reasoning-oriented geo-localization dataset, MP16-Reason, using diverse social media images.<n>GLOBE incorporates task-specific rewards that jointly enhance localizability assessment, visual-cue reasoning, and geolocation accuracy.<n>Results demonstrate that GLOBE outperforms state-of-the-art open-source LVLMs on geo-localization tasks.
  arXiv  Detail & Related papers  (2025-06-17T16:07:58Z)
• SegEarth-R1: Geospatial Pixel Reasoning via Large Language Model [61.97017867656831]
  We introduce a new task, ie, geospatial pixel reasoning, which allows implicit querying and reasoning and generates the mask of the target region.<n>We construct and release the first large-scale benchmark dataset called EarthReason, which comprises 5,434 manually annotated image masks with over 30,000 implicit question-answer pairs.<n>SegEarth-R1 achieves state-of-the-art performance on both reasoning and referring segmentation tasks, significantly outperforming traditional and LLM-based segmentation methods.
  arXiv  Detail & Related papers  (2025-04-13T16:36:47Z)
• SegDesicNet: Lightweight Semantic Segmentation in Remote Sensing with Geo-Coordinate Embeddings for Domain Adaptation [0.5461938536945723]
  We propose a novel unsupervised domain adaptation technique for remote sensing semantic segmentation.<n>Our proposed SegDesicNet module regresses the GRID positional encoding of the geo coordinates projected over the unit sphere to obtain the domain loss.<n>Our algorithm seeks to reduce the modeling disparity between artificial neural networks and human comprehension of the physical world.
  arXiv  Detail & Related papers  (2025-03-11T11:01:18Z)
• CLIP the Gap: A Single Domain Generalization Approach for Object Detection [60.20931827772482]
  Single Domain Generalization tackles the problem of training a model on a single source domain so that it generalizes to any unseen target domain. We propose to leverage a pre-trained vision-language model to introduce semantic domain concepts via textual prompts. We achieve this via a semantic augmentation strategy acting on the features extracted by the detector backbone, as well as a text-based classification loss.
  arXiv  Detail & Related papers  (2023-01-13T12:01:18Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.