GRASP: Geospatial pixel Reasoning viA Structured Policy learning

• URL: http://arxiv.org/abs/2508.17102v2
• Date: Tue, 28 Oct 2025 06:06:16 GMT
• Title: GRASP: Geospatial pixel Reasoning viA Structured Policy learning
• Authors: Chengjie Jiang, Yunqi Zhou, Jiafeng Yan, Jing Li, Jiayang Li, Yue Zhou, Hongjie He, Jonathan Li,
• Abstract summary: GRASP is a structured policy-learning framework that integrates a multimodal large language model with a pretrained segmentation model in a cascaded manner.<n> PRIME is a training paradigm that replaces supervised fine-tuning with reinforcement learning to better align reasoning and grounding behaviors with task objectives.<n>We release GRASP-1k, a fully out-of-domain benchmark with reasoning-intensive queries, reasoning traces, and fine-grained masks.
• Score: 16.023628299873494
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Geospatial pixel reasoning aims to generate segmentation masks in remote sensing imagery directly from natural-language instructions. Most existing approaches follow a paradigm that fine-tunes multimodal large language models under supervision with dense pixel-level masks as ground truth. While effective within the training data distribution, this design suffers from two main drawbacks: (1) the high cost of large-scale dense mask annotation, and (2) the limited generalization capability of supervised fine-tuning in out-of-domain scenarios. To address these issues, we propose GRASP, a structured policy-learning framework that integrates a multimodal large language model with a pretrained segmentation model in a cascaded manner. To enhance generalization, we introduce PRIME, a training paradigm that replaces supervised fine-tuning with reinforcement learning to better align reasoning and grounding behaviors with task objectives. To reduce annotation costs, we design BoP-Rewards, which substitutes dense mask labels with bounding box and positive points. It further verifies outputs through two complementary signals: format, which constrains the reasoning and grounding structure to remain syntactically parsable, and accuracy, which evaluates the quality of predicted boxes and points. For evaluation, we train our method and all baselines on EarthReason and GeoPixInstruct, constructing an in-domain benchmark by merging their test sets. We further release GRASP-1k, a fully out-of-domain benchmark with reasoning-intensive queries, reasoning traces, and fine-grained masks. Experimental results demonstrate state-of-the-art (SOTA) in-domain performance and up to 54\% improvement in out-of-domain scenarios, confirming that reinforcement learning with cost-aware rewards provides a robust and scalable paradigm for geospatial pixel reasoning. All code and datasets will be released publicly.

Related papers

• ResAgent: Entropy-based Prior Point Discovery and Visual Reasoning for Referring Expression Segmentation [21.87321809019825]
  Referring Expression (RES) is a core vision-language segmentation task that enables pixel-level understanding of targets via free-form linguistic expressions.<n>textbfmodel is a novel RES framework integrating textbfEntropy-textbfBased Point textbfDiscovery (textbfEBD) and textbfVision-textbfBased textbfReasoning (textbfVBR)<n>model implements a coarse-to
  arXiv  Detail & Related papers  (2026-01-23T01:56:04Z)
• MinerU2.5: A Decoupled Vision-Language Model for Efficient High-Resolution Document Parsing [117.58619053719251]
  MinerU2.5 is a document parsing model that achieves state-of-the-art recognition accuracy while maintaining exceptional computational efficiency.<n>Our approach employs a coarse-to-fine, two-stage parsing strategy that decouples global layout analysis from local content recognition.
  arXiv  Detail & Related papers  (2025-09-26T10:45:48Z)
• Two Facets of the Same Optimization Coin: Model Degradation and Representation Collapse in Graph Foundation Models [41.39154912912367]
  GFMs are designed to learn the optimal embedding functions from multi-domain text-attributed graphs.<n> graph VQ-MAE stands out among the increasingly diverse landscape of GFM.<n>Despite its potential, domain generalization conflicts cause imperceptible pitfalls.
  arXiv  Detail & Related papers  (2025-09-10T08:45:08Z)
• Enhancing Spatial Reasoning in Vision-Language Models via Chain-of-Thought Prompting and Reinforcement Learning [0.42855555838080844]
  This study investigates the spatial reasoning capabilities of vision-language models (VLMs) through Chain-of-Thought prompting and reinforcement learning.<n>We find that simple CoT formats, where the model generates a reasoning step before the answer, can harm the model's original performance.<n>In contrast, structured multi-stage prompting based on scene graphs (SceneGraph CoT) significantly improves spatial reasoning accuracy.
  arXiv  Detail & Related papers  (2025-07-06T10:51:12Z)
• Topology-Aware Modeling for Unsupervised Simulation-to-Reality Point Cloud Recognition [63.55828203989405]
  We introduce a novel Topology-Aware Modeling (TAM) framework for Sim2Real UDA on object point clouds.<n>Our approach mitigates the domain gap by leveraging global spatial topology, characterized by low-level, high-frequency 3D structures.<n>We propose an advanced self-training strategy that combines cross-domain contrastive learning with self-training.
  arXiv  Detail & Related papers  (2025-06-26T11:53:59Z)
• ReGUIDE: Data Efficient GUI Grounding via Spatial Reasoning and Search [53.40810298627443]
  ReGUIDE is a framework for web grounding that enables MLLMs to learn data efficiently through self-generated reasoning and spatial-aware criticism.<n>Our experiments demonstrate that ReGUIDE significantly advances web grounding performance across multiple benchmarks.
  arXiv  Detail & Related papers  (2025-05-21T08:36:18Z)
• P2Object: Single Point Supervised Object Detection and Instance Segmentation [58.778288785355]
  We introduce Point-to-Box Network (P2BNet), which constructs balanced textbftextitinstance-level proposal bags<n>P2MNet can generate more precise bounding boxes and generalize to segmentation tasks.<n>Our method largely surpasses the previous methods in terms of the mean average precision on COCO, VOC, and Cityscapes.
  arXiv  Detail & Related papers  (2025-04-10T14:51:08Z)
• Unsupervised Pre-training with Language-Vision Prompts for Low-Data Instance Segmentation [105.23631749213729]
  We propose a novel method for unsupervised pre-training in low-data regimes. Inspired by the recently successful prompting technique, we introduce a new method, Unsupervised Pre-training with Language-Vision Prompts. We show that our method can converge faster and perform better than CNN-based models in low-data regimes.
  arXiv  Detail & Related papers  (2024-05-22T06:48:43Z)
• Annotation Free Semantic Segmentation with Vision Foundation Models [11.026377387506216]
  We generate free annotations for any semantic segmentation dataset using existing foundation models. We use CLIP to detect objects and SAM to generate high quality object masks. Our approach can bring language-based semantics to any pretrained vision encoder with minimal training.
  arXiv  Detail & Related papers  (2024-03-14T11:57:58Z)
• UGMAE: A Unified Framework for Graph Masked Autoencoders [67.75493040186859]
  We propose UGMAE, a unified framework for graph masked autoencoders. We first develop an adaptive feature mask generator to account for the unique significance of nodes. We then design a ranking-based structure reconstruction objective joint with feature reconstruction to capture holistic graph information.
  arXiv  Detail & Related papers  (2024-02-12T19:39:26Z)
• Weakly-supervised Contrastive Learning for Unsupervised Object Discovery [52.696041556640516]
  Unsupervised object discovery is promising due to its ability to discover objects in a generic manner. We design a semantic-guided self-supervised learning model to extract high-level semantic features from images. We introduce Principal Component Analysis (PCA) to localize object regions.
  arXiv  Detail & Related papers  (2023-07-07T04:03:48Z)
• A Simple Framework for Open-Vocabulary Segmentation and Detection [85.21641508535679]
  We present OpenSeeD, a simple Open-vocabulary and Detection framework that jointly learns from different segmentation and detection datasets. We first introduce a pre-trained text encoder to encode all the visual concepts in two tasks and learn a common semantic space for them. After pre-training, our model exhibits competitive or stronger zero-shot transferability for both segmentation and detection.
  arXiv  Detail & Related papers  (2023-03-14T17:58:34Z)
• Grounding Visual Representations with Texts for Domain Generalization [9.554646174100123]
  Cross-modality supervision can be successfully used to ground domain-invariant visual representations. Our proposed method achieves state-of-the-art results and ranks 1st in average performance for five multi-domain datasets.
  arXiv  Detail & Related papers  (2022-07-21T03:43:38Z)
• Semi-supervised Domain Adaptive Structure Learning [72.01544419893628]
  Semi-supervised domain adaptation (SSDA) is a challenging problem requiring methods to overcome both 1) overfitting towards poorly annotated data and 2) distribution shift across domains. We introduce an adaptive structure learning method to regularize the cooperation of SSL and DA.
  arXiv  Detail & Related papers  (2021-12-12T06:11:16Z)
• SSA: Semantic Structure Aware Inference for Weakly Pixel-Wise Dense Predictions without Cost [36.27226683586425]
  The semantic structure aware inference (SSA) is proposed to explore the semantic structure information hidden in different stages of the CNN-based network to generate high-quality CAM in the model inference. The proposed method has the advantage of no parameters and does not need to be trained. Therefore, it can be applied to a wide range of weakly-supervised pixel-wise dense prediction tasks.
  arXiv  Detail & Related papers  (2021-11-05T11:07:21Z)
• Remote Sensing Images Semantic Segmentation with General Remote Sensing Vision Model via a Self-Supervised Contrastive Learning Method [13.479068312825781]
  We propose Global style and Local matching Contrastive Learning Network (GLCNet) for remote sensing semantic segmentation. Specifically, the global style contrastive module is used to learn an image-level representation better. The local features matching contrastive module is designed to learn representations of local regions which is beneficial for semantic segmentation.
  arXiv  Detail & Related papers  (2021-06-20T03:03:40Z)
• Group-Wise Semantic Mining for Weakly Supervised Semantic Segmentation [49.90178055521207]
  This work addresses weakly supervised semantic segmentation (WSSS), with the goal of bridging the gap between image-level annotations and pixel-level segmentation. We formulate WSSS as a novel group-wise learning task that explicitly models semantic dependencies in a group of images to estimate more reliable pseudo ground-truths. In particular, we devise a graph neural network (GNN) for group-wise semantic mining, wherein input images are represented as graph nodes.
  arXiv  Detail & Related papers  (2020-12-09T12:40:13Z)
• Adversarial Bipartite Graph Learning for Video Domain Adaptation [50.68420708387015]
  Domain adaptation techniques, which focus on adapting models between distributionally different domains, are rarely explored in the video recognition area. Recent works on visual domain adaptation which leverage adversarial learning to unify the source and target video representations are not highly effective on the videos. This paper proposes an Adversarial Bipartite Graph (ABG) learning framework which directly models the source-target interactions.
  arXiv  Detail & Related papers  (2020-07-31T03:48:41Z)

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.