Vision Mamba in Remote Sensing: A Comprehensive Survey of Techniques, Applications and Outlook

2025-05-01

AI Summary

Convolutional neural networks (CNNs) suffer from limited receptive fields, while vision transformers (ViTs) incur quadratic computational complexity—two critical bottlenecks in high-resolution remote sensing image analysis. Method: This work pioneers a systematic investigation of state space models (SSMs), particularly Mamba, for remote sensing. We conduct a comprehensive survey of 120 studies to establish a task-oriented taxonomy; propose a five-dimensional analytical framework covering principles, architectures, evaluation protocols, challenges, and future directions; and release the first open-source remote sensing Mamba repository. Furthermore, we design a CNN-Transformer-Mamba hybrid architecture, adaptive scanning strategies, and frequency-domain adaptation techniques. Contribution/Results: Our approach achieves linear computational complexity and robust global modeling, demonstrating consistent performance gains across object detection, semantic segmentation, and change detection. We establish Mamba as a new paradigm for intelligent remote sensing analysis and advance the scalable deployment of SSMs in high-resolution remote sensing applications.

Technology Category

• Computer Vision: Remote Sensing / Geospatial AI
• Intelligent Robots: Multimodal Perception & Sensor Fusion
• Machine Learning: Large Multimodal Models (LMMs)

Application Category

• Search and Retrieval-Augmented AI: Web query analysis, representation and understanding
• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs
• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications

Abstract

Deep learning has profoundly transformed remote sensing, yet prevailing architectures like Convolutional Neural Networks (CNNs) and Vision Transformers (ViTs) remain constrained by critical trade-offs: CNNs suffer from limited receptive fields, while ViTs grapple with quadratic computational complexity, hindering their scalability for high-resolution remote sensing data. State Space Models (SSMs), particularly the recently proposed Mamba architecture, have emerged as a paradigm-shifting solution, combining linear computational scaling with global context modeling. This survey presents a comprehensive review of Mamba-based methodologies in remote sensing, systematically analyzing about 120 studies to construct a holistic taxonomy of innovations and applications. Our contributions are structured across five dimensions: (i) foundational principles of vision Mamba architectures, (ii) micro-architectural advancements such as adaptive scan strategies and hybrid SSM formulations, (iii) macro-architectural integrations, including CNN-Transformer-Mamba hybrids and frequency-domain adaptations, (iv) rigorous benchmarking against state-of-the-art methods in multiple application tasks, such as object detection, semantic segmentation, change detection, etc. and (v) critical analysis of unresolved challenges with actionable future directions. By bridging the gap between SSM theory and remote sensing practice, this survey establishes Mamba as a transformative framework for remote sensing analysis. To our knowledge, this paper is the first systematic review of Mamba architectures in remote sensing. Our work provides a structured foundation for advancing research in remote sensing systems through SSM-based methods. We curate an open-source repository (https://github.com/BaoBao0926/Awesome-Mamba-in-Remote-Sensing) to foster community-driven advancements.

Problem

• Addressing CNN's limited receptive fields in remote sensing
• Overcoming ViT's quadratic computational complexity for scalability
• Exploring Mamba's linear scaling and global context modeling

Innovation

• Mamba architecture combines linear scaling with global context
• Hybrid CNN-Transformer-Mamba for enhanced remote sensing
• Adaptive scan strategies improve SSM efficiency