Mitigate Target-level Insensitivity of Infrared Small Target Detection via Posterior Distribution Modeling

TL;DR

This paper introduces a diffusion model framework with posterior distribution modeling and wavelet-based noise suppression for infrared small target detection, effectively overcoming target-level insensitivity and improving detection performance.

Contribution

It proposes a novel generative diffusion model approach with posterior distribution modeling and wavelet domain noise suppression for IRSTD, addressing limitations of discriminative methods.

Findings

Achieves competitive results on multiple IRSTD datasets.

Outperforms state-of-the-art methods in detection accuracy.

Demonstrates robustness against infrared noise interference.

Abstract

Infrared Small Target Detection (IRSTD) aims to segment small targets from infrared clutter background. Existing methods mainly focus on discriminative approaches, i.e., a pixel-level front-background binary segmentation. Since infrared small targets are small and low signal-to-clutter ratio, empirical risk has few disturbances when a certain false alarm and missed detection exist, which seriously affect the further improvement of such methods. Motivated by the dense prediction generative methods, in this paper, we propose a diffusion model framework for Infrared Small Target Detection which compensates pixel-level discriminant with mask posterior distribution modeling. Furthermore, we design a Low-frequency Isolation in the wavelet domain to suppress the interference of intrinsic infrared noise on the diffusion noise estimation. This transition from the discriminative paradigm to generative one enables us to bypass the target-level insensitivity. Experiments show that the proposed method achieves competitive performance gains over state-of-the-art methods on NUAA-SIRST, IRSTD-1k, and NUDT-SIRST datasets. Code are available at https://github.com/Li-Haoqing/IRSTD-Diff.