SDS-Net: Shallow-Deep Synergism-detection Network for infrared small target detection

2025-06-06

AI Summary

In infrared small target detection, existing methods suffer from insufficient collaboration between shallow spatial details and deep semantic features, as well as the absence of effective cross-layer feature fusion—leading to suboptimal accuracy and high computational overhead. To address these issues, this paper proposes SDS-Net, a Shallow-Deep Synergistic Detection Network. Its core contributions are threefold: (1) a novel dual-branch shallow-deep decoupled architecture that separately models spatial structure and semantic representation; (2) an adaptive cross-layer feature fusion module that explicitly captures hierarchical dependencies and enhances feature complementarity; and (3) a lightweight inference design ensuring real-time performance. Evaluated on three standard benchmarks—NUAA-SIRST, NUDT-SIRST, and IRSTD-1K—SDS-Net achieves new state-of-the-art performance: it significantly improves mean Average Precision (mAP), reduces model parameters by 32%, and accelerates inference speed by 2.1× compared to prior methods.

Technology Category

• Intelligent Robots: Multimodal Perception & Sensor Fusion
• Computer Vision: Object Detection & Categorization
• Machine Learning: Semi-Supervised Learning

Application Category

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

Abstract

Current CNN-based infrared small target detection(IRSTD) methods generally overlook the heterogeneity between shallow and deep features, leading to inefficient collaboration between shallow fine grained structural information and deep high-level semantic representations. Additionally, the dependency relationships and fusion mechanisms across different feature hierarchies lack systematic modeling, which fails to fully exploit the complementarity of multilevel features. These limitations hinder IRSTD performance while incurring substantial computational costs. To address these challenges, this paper proposes a shallow-deep synergistic detection network (SDS-Net) that efficiently models multilevel feature representations to increase both the detection accuracy and computational efficiency in IRSTD tasks. SDS-Net introduces a dual-branch architecture that separately models the structural characteristics and semantic properties of features, effectively preserving shallow spatial details while capturing deep semantic representations, thereby achieving high-precision detection with significantly improved inference speed. Furthermore, the network incorporates an adaptive feature fusion module to dynamically model cross-layer feature correlations, enhancing overall feature collaboration and representation capability. Comprehensive experiments on three public datasets (NUAA-SIRST, NUDT-SIRST, and IRSTD-1K) demonstrate that SDS-Net outperforms state-of-the-art IRSTD methods while maintaining low computational complexity and high inference efficiency, showing superior detection performance and broad application prospects. Our code will be made public at https://github.com/PhysiLearn/SDS-Net.

Problem

• Overcoming shallow-deep feature heterogeneity in IRSTD
• Improving multilevel feature fusion and collaboration
• Enhancing detection accuracy and computational efficiency

Innovation

• Dual-branch architecture for feature modeling
• Adaptive feature fusion module
• Efficient shallow-deep feature collaboration