arXiv:2504.12795v3 Announce Type: replace 
Abstract: Recent advances in natural-domain multi-modal large language models (MLLMs) have demonstrated effective spatial reasoning through visual and textual prompting. However, their direct transfer to remote sensing (RS) is hindered by heterogeneous sensing physics, diverse modalities, and unique spatial scales. Existing RS MLLMs are mainly limited to optical imagery and plain language interaction, preventing flexible and scalable real-world applications. In this article, EarthGPT-X is proposed, the first flexible spatial MLLM that unifies multi-source RS imagery comprehension and accomplishes both coarse-grained and fine-grained visual tasks under diverse visual prompts in a single framework. Distinct from prior models, EarthGPT-X introduces: 1) a dual-prompt mechanism combining text instructions with various visual prompts (i.e., point, box, and free-form) to mimic the versatility of referring in human life; 2) a comprehensive multi-source multi-level prompting dataset, the model advances beyond holistic image understanding to support hierarchical spatial reasoning, including scene-level understanding and fine-grained object attributes and relational analysis; 3) a cross-domain one-stage fusion training strategy, enabling efficient and consistent alignment across modalities and tasks. Extensive experiments demonstrate that EarthGPT-X substantially outperforms prior nature and RS MLLMs, establishing the first framework capable of multi-source, multi-task, and multi-level interpretation using visual prompting in RS scenarios.

EarthGPT-X هو تطوير ثوري في مجال الاستشعار عن بعد، حيث يستخدم نماذج اللغة الكبيرة متعددة الوسائط لتعزيز التفكير المكاني من خلال التحفيز البصري. تتناول هذه الابتكار التحديات التي تطرحها أنماط الاستشعار المتنوعة والمقاييس المكانية، والتي كانت قد حدت سابقًا من فعالية النماذج الحالية. من خلال تمكين تفاعلات أكثر مرونة وقابلية للتوسع مع صور الاستشعار عن بعد، يمتلك EarthGPT-X القدرة على تحسين تحليل البيانات واتخاذ القرارات في تطبيقات متنوعة، مما يجعله تقدمًا ملحوظًا في التكنولوجيا.

EarthGPT-X es un desarrollo innovador en el campo de la teledetección, que aprovecha modelos de lenguaje grande multimodal para mejorar el razonamiento espacial a través de la indicación visual. Esta innovación aborda los desafíos que presentan las diversas modalidades de detección y escalas espaciales, que anteriormente limitaron la efectividad de los modelos existentes. Al permitir interacciones más flexibles y escalables con las imágenes de teledetección, EarthGPT-X tiene el potencial de mejorar significativamente el análisis de datos y la toma de decisiones en diversas aplicaciones, lo que lo convierte en un avance notable en la tecnología.

EarthGPT-X est un développement révolutionnaire dans le domaine de la télédétection, utilisant des modèles de langage large multimodaux avancés pour améliorer le raisonnement spatial grâce à l'invite visuelle. Cette innovation répond aux défis posés par les modalités de détection diverses et les échelles spatiales, qui ont auparavant limité l'efficacité des modèles existants. En permettant des interactions plus flexibles et évolutives avec les images de télédétection, EarthGPT-X a le potentiel d'améliorer considérablement l'analyse des données et la prise de décision dans diverses applications, ce qui en fait une avancée remarquable dans la technologie.

EarthGPT-X is a groundbreaking development in the field of remote sensing, leveraging advanced multi-modal large language models to enhance spatial reasoning through visual prompting. This innovation addresses the challenges posed by diverse sensing modalities and spatial scales, which have previously limited the effectiveness of existing models. By enabling more flexible and scalable interactions with remote sensing imagery, EarthGPT-X has the potential to significantly improve data analysis and decision-making in various applications, making it a noteworthy advancement in technology.

EarthGPT-X: A Spatial MLLM for Multi-level Multi-Source Remote Sensing Imagery Understanding with Visual Prompting

arXiv:2601.08446v1 Announce Type: cross 
Abstract: The development of reliable methods for multi-label classification (MLC) has become a prominent research direction in remote sensing (RS). As the scale of RS data continues to expand, annotation procedures increasingly rely on thematic products or crowdsourced procedures to reduce the cost of manual annotation. While cost-effective, these strategies often introduce multi-label noise in the form of partially incorrect annotations. In MLC, label noise arises as additive noise, subtractive noise, or a combination of both in the form of mixed noise. Previous work has largely overlooked this distinction and commonly treats noisy annotations as supervised signals, lacking mechanisms that explicitly adapt learning behavior to different noise types. To address this limitation, we propose NAR, a noise-adaptive regularization method that explicitly distinguishes between additive and subtractive noise within a semi-supervised learning framework. NAR employs a confidence-based label handling mechanism that dynamically retains label entries with high confidence, temporarily deactivates entries with moderate confidence, and corrects low confidence entries via flipping. This selective attenuation of supervision is integrated with early-learning regularization (ELR) to stabilize training and mitigate overfitting to corrupted labels. Experiments across additive, subtractive, and mixed noise scenarios demonstrate that NAR consistently improves robustness compared with existing methods. Performance improvements are most pronounced under subtractive and mixed noise, indicating that adaptive suppression and selective correction of noisy supervision provide an effective strategy for noise robust learning in RS MLC.

تم اقتراح طريقة جديدة تُدعى التنظيم التكيفي للضوضاء (NAR) لتحسين التصنيف متعدد التسميات في استشعار عن بُعد، حيث تتناول التحديات التي تطرحها التعليقات المزعجة التي قد تنشأ من طرق جمع البيانات ذات التكلفة المنخفضة. يميز NAR بين الضوضاء المضافة والضوضاء المخصومة ضمن إطار التعلم شبه الموجه، مما يعزز من قوة تصنيف الصور.

Se ha propuesto un nuevo método llamado Regularización Adaptativa al Ruido (NAR) para mejorar la clasificación multi-etiqueta en la teledetección, abordando los desafíos que presentan las anotaciones ruidosas que pueden surgir de métodos de recolección de datos rentables. NAR distingue entre ruido aditivo y ruido sustractivo dentro de un marco de aprendizaje semi-supervisado, mejorando así la robustez de la clasificación de imágenes.

Une nouvelle méthode appelée Régularisation Adaptative au Bruit (NAR) a été proposée pour améliorer la classification multi-étiquettes dans la télédétection, en abordant les défis posés par les annotations bruyantes qui peuvent découler de méthodes de collecte de données rentables. NAR distingue entre le bruit additif et le bruit soustractif dans un cadre d'apprentissage semi-supervisé, renforçant ainsi la robustesse de la classification d'images.

A new method called Noise-Adaptive Regularization (NAR) has been proposed to improve multi-label classification in remote sensing, addressing the challenges posed by noisy annotations that can arise from cost-effective data collection methods. NAR distinguishes between additive and subtractive noise within a semi-supervised learning framework, enhancing the robustness of image classification.

Noise-Adaptive Regularization for Robust Multi-Label Remote Sensing Image Classification

One More Thing in AI – Your Shortcut to AI Mastery

EarthGPT-X: A Spatial MLLM for Multi-level Multi-Source Remote Sensing Imagery Understanding with Visual Prompting

Was this article worth reading? Share it

One More Thing in AI

LucidQuery AI

Attentive AI

The Visualizer

Guidejar-4eb95b

Scop.ai

Ready to build your own newsroom?