ARFC-WAHNet: Adaptive Receptive Field Convolution and Wavelet-Attentive Hierarchical Network for Infrared Small Target Detection

2025-05-15

AI Summary

Infrared small target detection (ISTD) remains highly challenging due to low texture, absent structural cues, and strong background clutter. Conventional deep learning approaches relying on fixed-receptive-field convolutions and pooling suffer from limited spatial adaptability, severe feature degradation, and poor noise robustness. To address these issues, we propose a novel detection network featuring: (i) multi-receptive-field feature interaction convolution for adaptive spatial modeling; (ii) Haar wavelet-based frequency-domain enhanced downsampling to preserve critical details while suppressing noise; and (iii) a gated high–low-level fusion module coupled with global median-enhanced attention to strengthen contextual awareness and target discriminability. Extensive experiments on SIRST, NUDT-SIRST, and IRSTD-1k benchmarks demonstrate that our method achieves state-of-the-art performance, with significant improvements in detection accuracy and robustness against complex backgrounds.

Technology Category

• Intelligent Robots: Multimodal Perception & Sensor Fusion
• Computer Vision: Adversarial Attacks & Robustness
• Machine Learning: Multi-instance/Multi-view Learning

Application Category

• Search and Retrieval-Augmented AI: Web query analysis, representation and understanding
• Web Mining and Content Analysis: Normalization, clustering, classification, and summarization of Web text
• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications

Abstract

Infrared small target detection (ISTD) is critical in both civilian and military applications. However, the limited texture and structural information in infrared images makes accurate detection particularly challenging. Although recent deep learning-based methods have improved performance, their use of conventional convolution kernels limits adaptability to complex scenes and diverse targets. Moreover, pooling operations often cause feature loss and insufficient exploitation of image information. To address these issues, we propose an adaptive receptive field convolution and wavelet-attentive hierarchical network for infrared small target detection (ARFC-WAHNet). This network incorporates a multi-receptive field feature interaction convolution (MRFFIConv) module to adaptively extract discriminative features by integrating multiple convolutional branches with a gated unit. A wavelet frequency enhancement downsampling (WFED) module leverages Haar wavelet transform and frequency-domain reconstruction to enhance target features and suppress background noise. Additionally, we introduce a high-low feature fusion (HLFF) module for integrating low-level details with high-level semantics, and a global median enhancement attention (GMEA) module to improve feature diversity and expressiveness via global attention. Experiments on public datasets SIRST, NUDT-SIRST, and IRSTD-1k demonstrate that ARFC-WAHNet outperforms recent state-of-the-art methods in both detection accuracy and robustness, particularly under complex backgrounds. The code is available at https://github.com/Leaf2001/ARFC-WAHNet.

Problem

• Detecting infrared small targets with limited texture information
• Overcoming feature loss from conventional convolution and pooling
• Improving detection accuracy in complex backgrounds

Innovation

• Adaptive receptive field convolution for feature extraction
• Wavelet frequency enhancement for noise suppression
• Hierarchical fusion of low and high-level features