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

TL;DR

SDS-Net is a novel infrared small target detection network that effectively combines shallow and deep features through a dual-branch architecture and adaptive fusion, achieving high accuracy and efficiency.

Contribution

The paper introduces SDS-Net, a dual-branch network with adaptive feature fusion for improved multilevel feature modeling in IRSTD tasks.

Findings

Outperforms state-of-the-art methods on three datasets

Achieves high detection accuracy with low computational cost

Demonstrates superior inference speed and broad application potential

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.