DRPCA-Net: Make Robust PCA Great Again for Infrared Small Target Detection

2025-07-13

AI Summary

Infrared small target detection suffers from poor model interpretability, parameter redundancy, and limited generalization—primarily due to the neglect of the inherent sparse prior in infrared imagery by existing deep learning methods. To address this, we propose DRPCA-Net, a dynamic network that integrates the sparse prior from Robust Principal Component Analysis (RPCA) into a deep unfolding architecture. Its core innovations include: (i) a lightweight hypernetwork-driven dynamic parameter generation mechanism enabling input-adaptive iterative unfolding, and (ii) a spatiotemporal context-aware dynamic residual group to enhance background modeling and small target separation. Evaluated on multiple public infrared datasets, DRPCA-Net achieves significant improvements over state-of-the-art methods, demonstrating superior detection accuracy, strong cross-dataset generalization, and high parameter efficiency.

Technology Category

• Computer Vision: Adversarial Attacks & Robustness
• Intelligent Robots: Multimodal Perception & Sensor Fusion
• 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
• Graph Algorithms and Modeling for the Web: Efficient manipulation of static and dynamic Web-related graphs
• Web Mining and Content Analysis: Large pretrained models with web data

Abstract

Infrared small target detection plays a vital role in remote sensing, industrial monitoring, and various civilian applications. Despite recent progress powered by deep learning, many end-to-end convolutional models tend to pursue performance by stacking increasingly complex architectures, often at the expense of interpretability, parameter efficiency, and generalization. These models typically overlook the intrinsic sparsity prior of infrared small targets--an essential cue that can be explicitly modeled for both performance and efficiency gains. To address this, we revisit the model-based paradigm of Robust Principal Component Analysis (RPCA) and propose Dynamic RPCA Network (DRPCA-Net), a novel deep unfolding network that integrates the sparsity-aware prior into a learnable architecture. Unlike conventional deep unfolding methods that rely on static, globally learned parameters, DRPCA-Net introduces a dynamic unfolding mechanism via a lightweight hypernetwork. This design enables the model to adaptively generate iteration-wise parameters conditioned on the input scene, thereby enhancing its robustness and generalization across diverse backgrounds. Furthermore, we design a Dynamic Residual Group (DRG) module to better capture contextual variations within the background, leading to more accurate low-rank estimation and improved separation of small targets. Extensive experiments on multiple public infrared datasets demonstrate that DRPCA-Net significantly outperforms existing state-of-the-art methods in detection accuracy. Code is available at https://github.com/GrokCV/DRPCA-Net.

Problem

• Improves infrared small target detection using sparse-aware deep learning
• Enhances Robust PCA with dynamic, input-adaptive parameter generation
• Addresses interpretability and efficiency in target detection models

Innovation

• Dynamic RPCA Network with deep unfolding
• Lightweight hypernetwork for adaptive parameters
• Dynamic Residual Group for context capture