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.
Ji-Yang Dong, Peipei Song, Yongchao Song et al.· IEEE Journal of Selected Top...· 0 citations
Medical image segmentation is a critical task in computer-assisted diagnosis, but accurate delineation remains challenging in sensor-captured dermoscopic and endoscopic images because of low contrast, blurred boundaries, acquisition artifacts, and large appearance variations. Although CNN-based methods are effective in capturing local texture and boundary cues, they often struggle to explicitly model long-range dependencies and global structural relationships. Transformer-based architectures can capture global context, but their self-attention mechanism may become computationally costly when processing high-resolution feature maps. To address these challenges, we propose MGA-UNet, a frequency-aware multi-scale encoder–decoder segmentation framework that integrates wavelet-based frequency decomposition with Mamba-based long-range dependency modelling. Specifically, the Wavelet-Mamba feature extraction backbone (WMB) decomposes features into low- and high-frequency components to enhance boundary-aware representation, the Gated Multi-scale Aggregation Module (GMAM) aggregates parallel multi-scale encoder features and applies a content-dependent gate to the fused response, and the Adaptive Sparse Attention Module (ASAM) refines bottleneck representations with sparse attention for global semantic modelling. Across three independent runs with random seeds 42, 123, and 2026, MGA-UNet achieves mean Dice Similarity Coefficients of 88.92±0.04%, 88.01±0.07%, and 85.91±0.04% on ISIC2018, ISIC2017, and Kvasir-SEG, respectively. These results demonstrate competitive segmentation performance among the compared representative CNN-based, Transformer-based, and Mamba-based methods, including the recent H-VMUNet baseline. These results indicate that frequency-domain decomposition and state-space modelling can complement each other for accurate medical image segmentation, particularly in images with ambiguous boundaries and complex background interference.
Shuai-Kang Qiu, Xuan Wang, Kaile Su et al.· Italian National Conference...· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
