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

2025-05-15

AI Summary

Infrared small target detection (ISTD) suffers from inaccurate localization and weak contour perception under low signal-to-clutter ratio (SCR) and dense clutter conditions. To address these challenges, we propose a dual-path embedding network featuring three key innovations: (1) the Surrounding Convergence Prior Extraction Module (SCPEM), which models the gradient convergence property toward target centers; (2) the Dual-Branch Prior Embedding Architecture (DBPEA) and Attention-Guided Feature Enhancement Module (AGFEM), jointly enabling disentangled fusion of contour and saliency priors; and (3) multi-scale feature fusion integrated with gradient-guided saliency modeling. Extensive experiments demonstrate state-of-the-art performance on three benchmark datasets—NUDT-SIRST, IRSTD-1k, and NUAA-SIRST—achieving significant improvements in small target recall and localization accuracy. The source code is publicly available.

Technology Category

• Intelligent Robots: Multimodal Perception & Sensor Fusion
• Machine Learning: Multi-instance/Multi-view Learning
• Computer Vision: Other Foundations of Computer Vision

Application Category

• Search and Retrieval-Augmented AI: Web evaluation methodologies and metrics
• Graph Algorithms and Modeling for the Web: Graph embeddings and representation learning for Web-related graphs
• Web Mining and Content Analysis: Large pretrained models with web data

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.

Problem

• Improving dim target localization in infrared detection
• Enhancing contour perception under dense clutter
• Boosting saliency and structural priors for accuracy

Innovation

• Surround-convergent prior extraction module captures contour gradients
• Dual-branch architecture embeds saliency and structural priors optimally
• Attention-guided module refines features for better saliency estimation