Lightweight Deep Unfolding Networks with Enhanced Robustness for Infrared Small Target Detection

2025-09-09

AI Summary

To address parameter redundancy and poor noise robustness in deep unfolding networks for infrared small target detection (ISTD), this paper proposes a lightweight decoupled network, L-RPCANet. Methodologically, it integrates robust principal component analysis (RPCA) as a structural prior and designs a hierarchical bottleneck architecture to enable dynamic channel-wise compression and recovery. It further incorporates SE channel attention to enhance discriminative feature responses and embeds a learnable denoising module to suppress complex noise interference. Compared with state-of-the-art methods such as RPCANet, L-RPCANet achieves significant improvements in detection accuracy across multiple ISTD benchmarks, reduces model parameters by 32%–47%, and maintains stable performance under strong noise conditions. The source code is publicly available.

Technology Category

• Intelligent Robots: State Estimation
• Computer Vision: Adversarial Attacks & Robustness
• Machine Learning: Learning on the Edge & Model Compression

Application Category

• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications
• Responsible Web: Measurement, analysis, and circumvention of Web censorship

Abstract

Infrared small target detection (ISTD) is one of the key techniques in image processing. Although deep unfolding networks (DUNs) have demonstrated promising performance in ISTD due to their model interpretability and data adaptability, existing methods still face significant challenges in parameter lightweightness and noise robustness. In this regard, we propose a highly lightweight framework based on robust principal component analysis (RPCA) called L-RPCANet. Technically, a hierarchical bottleneck structure is constructed to reduce and increase the channel dimension in the single-channel input infrared image to achieve channel-wise feature refinement, with bottleneck layers designed in each module to extract features. This reduces the number of channels in feature extraction and improves the lightweightness of network parameters. Furthermore, a noise reduction module is embedded to enhance the robustness against complex noise. In addition, squeeze-and-excitation networks (SENets) are leveraged as a channel attention mechanism to focus on the varying importance of different features across channels, thereby achieving excellent performance while maintaining both lightweightness and robustness. Extensive experiments on the ISTD datasets validate the superiority of our proposed method compared with state-of-the-art methods covering RPCANet, DRPCANet, and RPCANet++. The code will be available at https://github.com/xianchaoxiu/L-RPCANet.

Problem

• Enhancing noise robustness in infrared small target detection
• Reducing parameter lightweightness in deep unfolding networks
• Improving channel-wise feature refinement for ISTD

Innovation

• Lightweight hierarchical bottleneck structure
• Noise reduction module for robustness
• Channel attention mechanism using SENets