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

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 article, we compensate pixel-level discriminant with mask posterior distribution modeling. Specifically, we propose a diffusion model framework for IRSTD. This generative framework maximizes the posterior distribution of the small target mask to surmount the performance bottleneck associated with minimizing discriminative empirical risk. This transition from the discriminative paradigm to generative one enables us to bypass the target-level insensitivity. Furthermore, we design a low-frequency isolation in wavelet domain to suppress the interference of intrinsic infrared noise on the diffusion noise estimation. The low-frequency component of the infrared image in the wavelet domain is processed by a neural network, and the high-frequency component is utilized to restore the targets information, to estimate the residuals of the enhanced features. Experiments show that the proposed method achieves competitive performance gains over state-of-the-art methods on NUAA-SIRST, NUDT-SIRST, and IRSTD-1 k datasets.

Keywords

• Deep learning
• diffusion model
• generative model
• infrared small target detection (IRSTD)