Exploiting Gaussian Agnostic Representation Learning with Diffusion Priors for Enhanced Infrared Small Target Detection

TL;DR

This paper introduces a novel Gaussian Agnostic Representation Learning framework with diffusion priors to improve infrared small target detection, especially under data scarcity, by enhancing model robustness and sample fidelity.

Contribution

It proposes the Gaussian Group Squeezer for non-uniform quantization and two-stage diffusion models for better real-world reconstruction, addressing data scarcity challenges in ISTD.

Findings

Enhanced detection robustness under data scarcity scenarios

Significant improvement in synthetic sample quality and fidelity

Outperforms state-of-the-art methods in various challenging conditions

Abstract

Infrared small target detection (ISTD) plays a vital role in numerous practical applications. In pursuit of determining the performance boundaries, researchers employ large and expensive manual-labeling data for representation learning. Nevertheless, this approach renders the state-of-the-art ISTD methods highly fragile in real-world challenges. In this paper, we first study the variation in detection performance across several mainstream methods under various scarcity -- namely, the absence of high-quality infrared data -- that challenge the prevailing theories about practical ISTD. To address this concern, we introduce the Gaussian Agnostic Representation Learning. Specifically, we propose the Gaussian Group Squeezer, leveraging Gaussian sampling and compression for non-uniform quantization. By exploiting a diverse array of training samples, we enhance the resilience of ISTD models against various challenges. Then, we introduce two-stage diffusion models for real-world reconstruction. By aligning quantized signals closely with real-world distributions, we significantly elevate the quality and fidelity of the synthetic samples. Comparative evaluations against state-of-the-art detection methods in various scarcity scenarios demonstrate the efficacy of the proposed approach.