CSPENet: Contour-Aware and Saliency Priors Embedding Network for Infrared Small Target Detection

TL;DR

CSPENet is a novel neural network designed for infrared small target detection, integrating contour and saliency priors to improve localization and contour perception in cluttered environments.

Contribution

The paper introduces a new network architecture with a surround-convergent prior extraction module and dual-branch priors embedding for enhanced detection accuracy.

Findings

Outperforms state-of-the-art methods on multiple datasets.

Effectively captures target contours and improves localization.

Enhances detection in dense clutter environments.

Abstract

Infrared small target detection (ISTD) plays a critical role in a wide range of civilian and military applications. Existing methods suffer from deficiencies in the localization of dim targets and the perception of contour information under dense clutter environments, severely limiting their detection performance. To tackle these issues, we propose a contour-aware and saliency priors embedding network (CSPENet) for ISTD. We first design a surround-convergent prior extraction module (SCPEM) that effectively captures the intrinsic characteristic of target contour pixel gradients converging toward their center. This module concurrently extracts two collaborative priors: a boosted saliency prior for accurate target localization and multi-scale structural priors for comprehensively enriching contour detail representation. Building upon this, we propose a dual-branch priors embedding architecture (DBPEA) that establishes differentiated feature fusion pathways, embedding these two priors at optimal network positions to achieve performance enhancement. Finally, we develop an attention-guided feature enhancement module (AGFEM) to refine feature representations and improve saliency estimation accuracy. Experimental results on public datasets NUDT-SIRST, IRSTD-1k, and NUAA-SIRST demonstrate that our CSPENet outperforms other state-of-the-art methods in detection performance. The code is available at https://github.com/IDIP2025/CSPENet.