RSNet: A Light Framework for The Detection of Multi-scale Remote Sensing Targets

2024-10-30

arXiv.org

AI Summary

To address the challenges of accuracy and efficiency in detecting small-scale ship targets in synthetic aperture radar (SAR) imagery under data scarcity and complex background conditions, this paper proposes a lightweight end-to-end detection framework. The method introduces a novel Waveletpool-ContextGuided backbone network and a Waveletpool-StarFusion neck architecture, incorporating wavelet pooling, context-guided attention, and star-shaped residual wavelet multiplication for feature fusion. Additionally, a Lightweight-Shared detection head is designed to jointly model multi-scale contextual information and high-dimensional nonlinear features with minimal parameters. The entire model contains only 1.49 million parameters and achieves state-of-the-art mAP₅₀:₉₅ scores of 72.5% on SSDD and 67.6% on HRSID—substantially outperforming existing approaches.

Technology Category

• Computer Vision: Learning & Optimization for CV
• Machine Learning: Learning on the Edge & Model Compression
• Intelligent Robots: Multimodal Perception & Sensor Fusion

Application Category

• Search and Retrieval-Augmented AI: Web evaluation methodologies and metrics
• Graph Algorithms and Modeling for the Web: Representation, reconstruction, and subgraph or motif discovery in Web-related graphs
• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications

Abstract

Recent advancements in synthetic aperture radar (SAR) ship detection using deep learning have significantly improved accuracy and speed, yet effectively detecting small objects in complex backgrounds with fewer parameters remains a challenge. This letter introduces RSNet, a lightweight framework constructed to enhance ship detection in SAR imagery. To ensure accuracy with fewer parameters, we proposed Waveletpool-ContextGuided (WCG) as its backbone, guiding global context understanding through multi-scale wavelet features for effective detection in complex scenes. Additionally, Waveletpool-StarFusion (WSF) is introduced as the neck, employing a residual wavelet element-wise multiplication structure to achieve higher dimensional nonlinear features without increasing network width. The Lightweight-Shared (LS) module is designed as detect components to achieve efficient detection through lightweight shared convolutional structure and multi-format compatibility. Experiments on the SAR Ship Detection Dataset (SSDD) and High-Resolution SAR Image Dataset (HRSID) demonstrate that RSNet achieves a strong balance between lightweight design and detection performance, surpassing many state-of-the-art detectors, reaching 72.5% and 67.6% in extbf{(mathbf{mAP_{.50:.95}}) }respectively with 1.49M parameters. Our code will be released soon.

Problem

• Deep Learning
• Aerial Target Recognition
• Limited Data Challenge

Innovation

• RSNet
• Waveletpool-ContextGuided
• Waveletpool-StarFusion