It's Not the Target, It's the Background: Rethinking Infrared Small Target Detection via Deep Patch-Free Low-Rank Representations

TL;DR

This paper introduces LRRNet, a deep learning framework that models infrared background backgrounds as low-rank structures for improved small target detection, achieving high accuracy and real-time speed.

Contribution

It is the first to directly learn low-rank background representations with deep neural networks in an end-to-end manner for IRSTD.

Findings

Outperforms 38 state-of-the-art methods in accuracy and robustness.

Achieves real-time detection at 82.34 FPS.

Demonstrates resilience to sensor noise on challenging datasets.

Abstract

\textcolor{blue}{This is the pre-acceptance version, to read the final version please go to \href{https://ieeexplore.ieee.org/document/11156113}{IEEE Transactions on Geoscience and Remote Sensing on IEEE Xplore}.} Infrared small target detection (IRSTD) remains a long-standing challenge in complex backgrounds due to low signal-to-clutter ratios (SCR), diverse target morphologies, and the absence of distinctive visual cues. While recent deep learning approaches aim to learn discriminative representations, the intrinsic variability and weak priors of small targets often lead to unstable performance. In this paper, we propose a novel end-to-end IRSTD framework, termed LRRNet, which leverages the low-rank property of infrared image backgrounds. Inspired by the physical compressibility of cluttered scenes, our approach adopts a compression--reconstruction--subtraction (CRS) paradigm to directly model structure-aware low-rank background representations in the image domain, without relying on patch-based processing or explicit matrix decomposition. To the best of our knowledge, this is the first work to directly learn low-rank background structures using deep neural networks in an end-to-end manner. Extensive experiments on multiple public datasets demonstrate that LRRNet outperforms 38 state-of-the-art methods in terms of detection accuracy, robustness, and computational efficiency. Remarkably, it achieves real-time performance with an average speed of 82.34 FPS. Evaluations on the challenging NoisySIRST dataset further confirm the model's resilience to sensor noise. The source code will be made publicly available upon acceptance.