Mamba-Enhanced Lightweight Remote Sensing Object Detection

Abstract

Remote sensing object detection (RSOD) aims to accurately identify and locate ground objects in remote sensing images, supporting applications, such as environmental monitoring, disaster assessment, uncrewed aerial vehicle perception, and satellite remote sensing. However, practical RSOD often requires real-time inference on large-scale high-resolution images under limited onboard or edge computing resources. Meanwhile, small objects, arbitrary orientations, complex backgrounds, and unstable imaging quality make it difficult for existing methods to balance lightweight deployment and high-precision detection. To address these challenges, we propose MELRNet, a Mamba-enhanced lightweight framework for remote sensing rotated object detection. Specifically, Mamba-style state space modeling is introduced into key semantic stages to capture long-range dependencies with linear complexity. A multi-scale receptive field aggregator is designed to enhance small-object and multiscale representation, while dynamic tanh normalization is adopted to improve feature stability with limited computational overhead. Extensive experiments on five benchmark datasets demonstrate that MELRNet achieves a favorable balance between lightweight design and high-precision rotated object detection.