FUSAR-GPT : A Spatiotemporal Feature-Embedded and Two-Stage Decoupled Visual Language Model for SAR Imagery

• URL: http://arxiv.org/abs/2602.19190v2
• Date: Thu, 26 Feb 2026 09:45:03 GMT
• Title: FUSAR-GPT : A Spatiotemporal Feature-Embedded and Two-Stage Decoupled Visual Language Model for SAR Imagery
• Authors: Xiaokun Zhang, Yi Yang, Ziqi Ye, Baiyun, Xiaorong Guo, Qingchen Fang, Ruyi Zhang, Xinpeng Zhou, Haipeng Wang,
• Abstract summary: FUSAR-GPT is a VLM specifically for Synthetic Aperture Radar (SAR) applications.<n>It embeds multi-source remote-sensing temporal features into the model's visual backbone via'spatiotemporal anchors'<n>It achieves state-of-the-art performance across several typical remote sensing visual-language benchmark tests.
• Score: 8.62554606349568
• License: http://creativecommons.org/licenses/by-nc-nd/4.0/
• Abstract: Research on the intelligent interpretation of all-weather, all-time Synthetic Aperture Radar (SAR) is crucial for advancing remote sensing applications. In recent years, although Visual Language Models (VLMs) have demonstrated strong open-world understanding capabilities on RGB images, their performance is severely limited when directly applied to the SAR field due to the complexity of the imaging mechanism, sensitivity to scattering features, and the scarcity of high-quality text corpora. To systematically address this issue, we constructed the inaugural SAR Image-Text-AlphaEarth feature triplet dataset and developed FUSAR-GPT, a VLM specifically for SAR. FUSAR-GPT innovatively introduces a geospatial baseline model as a 'world knowledge' prior and embeds multi-source remote-sensing temporal features into the model's visual backbone via 'spatiotemporal anchors', enabling dynamic compensation for the sparse representation of targets in SAR images. Furthermore, we designed a two-stage SFT strategy to decouple the knowledge injection and task execution of large models. The spatiotemporal feature embedding and the two-stage decoupling paradigm enable FUSAR-GPT to achieve state-of-the-art performance across several typical remote sensing visual-language benchmark tests, significantly outperforming mainstream baseline models by over 12%.

Related papers

• Scaling Text-to-Image Diffusion Transformers with Representation Autoencoders [74.72147962028265]
  Representation Autoencoders (RAEs) have shown distinct advantages in diffusion modeling on ImageNet.<n>We investigate whether this framework can scale to large-scale, freeform text-to-image (T2I) generation.
  arXiv  Detail & Related papers  (2026-01-22T18:58:16Z)
• Dual-domain Adaptation Networks for Realistic Image Super-resolution [81.34345637776408]
  Realistic image super-resolution (SR) focuses on transforming real-world low-resolution (LR) images into high-resolution (HR) ones.<n>Current methods struggle with limited real-world LR-HR data, impacting the learning of basic image features.<n>We introduce a novel approach, which is able to efficiently adapt pre-trained image SR models from simulated to real-world datasets.
  arXiv  Detail & Related papers  (2025-11-21T12:57:23Z)
• SARCLIP: A Vision Language Foundation Model for Semantic Understanding and Target Recognition in SAR Imagery [46.87845911116779]
  We introduce SARCLIP, the first vision language foundation model tailored for the SAR domain.<n>SARCLIP is trained using a contrastive vision language learning approach by domain transferring strategy.<n>Experiments on image-text retrieval and zero-shot classification tasks demonstrate the superior performance of SARCLIP.
  arXiv  Detail & Related papers  (2025-10-26T13:04:50Z)
• FUSAR-KLIP: Towards Multimodal Foundation Models for Remote Sensing [16.948824707021412]
  Cross-modal artificial intelligence has garnered widespread attention in recent years, achieving significant progress in the study of natural images.<n>Existing methods are mostly designed for RGB imagery, leaving a significant gap in modeling synthetic aperture radar (SAR) imagery.<n>This paper proposes FUSAR-KLIP, the first universal SAR multimodal foundational model, along with reusable data and evaluation baselines.
  arXiv  Detail & Related papers  (2025-09-28T15:03:25Z)
• Annotation-Free Open-Vocabulary Segmentation for Remote-Sensing Images [51.74614065919118]
  This paper introduces SegEarth-OV, the first framework for annotation-free open-vocabulary segmentation of RS images.<n>We propose SimFeatUp, a universal upsampler that robustly restores high-resolution spatial details from coarse features.<n>We also present a simple yet effective Global Bias Alleviation operation to subtract the inherent global context from patch features.
  arXiv  Detail & Related papers  (2025-08-25T14:22:57Z)
• Quantitative Comparison of Fine-Tuning Techniques for Pretrained Latent Diffusion Models in the Generation of Unseen SAR Images [0.0]
  We adapt an open-source text-to-image foundation model to the Synthetic Aperture Radar (SAR) modality.<n>We compare full fine-tuning and parameter-efficient Low-Rank Adaptation (LoRA) across the UNet diffusion backbone, the Variational Autoencoder (VAE) and the text encoders.<n>Our results show that a hybrid strategy-full UNet tuning with LoRA on the text encoders and a learned token embedding-best preserves SAR geometry and texture.
  arXiv  Detail & Related papers  (2025-06-16T09:48:01Z)
• SARChat-Bench-2M: A Multi-Task Vision-Language Benchmark for SAR Image Interpretation [12.32553804641971]
  Vision language models (VLMs) have made remarkable progress in natural language processing and image understanding.<n>This paper innovatively proposes the first large-scale multimodal dialogue dataset for SAR images, named SARChat-2M.
  arXiv  Detail & Related papers  (2025-02-12T07:19:36Z)
• Electrooptical Image Synthesis from SAR Imagery Using Generative Adversarial Networks [0.0]
  This research contributes to the field of remote sensing by bridging the gap between SAR and EO imagery. The results show significant improvements in interpretability, making SAR data more accessible for analysts familiar with EO imagery. Our research contributes to the field of remote sensing by bridging the gap between SAR and EO imagery, offering a novel tool for enhanced data interpretation.
  arXiv  Detail & Related papers  (2024-09-07T14:31:46Z)
• Visual Delta Generator with Large Multi-modal Models for Semi-supervised Composed Image Retrieval [50.72924579220149]
  Composed Image Retrieval (CIR) is a task that retrieves images similar to a query, based on a provided textual modification. Current techniques rely on supervised learning for CIR models using labeled triplets of the reference image, text, target image. We propose a new semi-supervised CIR approach where we search for a reference and its related target images in auxiliary data.
  arXiv  Detail & Related papers  (2024-04-23T21:00:22Z)
• RS-Mamba for Large Remote Sensing Image Dense Prediction [58.12667617617306]
  We propose the Remote Sensing Mamba (RSM) for dense prediction tasks in large VHR remote sensing images. RSM is specifically designed to capture the global context of remote sensing images with linear complexity. Our model achieves better efficiency and accuracy than transformer-based models on large remote sensing images.
  arXiv  Detail & Related papers  (2024-04-03T12:06:01Z)

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.