DCCS-Det: Directional Context and Cross-Scale-Aware Detector for Infrared Small Target

2026-01-23

IEEE Transactions on Geoscience and Remote Sensing

AI Summary

This work proposes DCCS-Det, a novel detector addressing the limitations in infrared small target detection caused by insufficient joint modeling of local and global features, feature redundancy, and semantic dilution, which collectively degrade discriminative capability and representation quality. The method introduces a Dual-stream Saliency Enhancement (DSE) module to integrate local perception with directional contextual awareness, and a Latent-variable-aware Cross-scale Semantic Extraction and Aggregation (LaSEA) module coupled with a stochastic pooling sampling strategy to enhance long-range dependencies while suppressing noise. Extensive experiments demonstrate that DCCS-Det achieves state-of-the-art accuracy across multiple infrared small target datasets while maintaining computational efficiency. Ablation studies further confirm the effectiveness of each component in improving target perception and feature representation.

Technology Category

• Computer Vision: Object Detection & Categorization
• Search and Optimization: Local Search
• Machine Learning: Calibration & Uncertainty Quantification

Application Category

• Search and Retrieval-Augmented AI: Vertical and domain-specific search
• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs
• Graph Algorithms and Modeling for the Web: Representation, reconstruction, and subgraph or motif discovery in Web-related graphs

Abstract

Infrared small target detection (IRSTD) is critical for applications like remote sensing and surveillance, which aims to identify small, low-contrast targets against complex backgrounds. However, existing methods often struggle with inadequate joint modeling of local–global features (harming target-background discrimination) or feature redundancy and semantic dilution (degrading target representation quality). To tackle these issues, we propose directional context and cross-scale-aware detector for infrared small target (DCCS-Det), a novel detector that incorporates a dual-stream saliency enhancement (DSE) block and a latent-aware semantic extraction and aggregation (LaSEA) module. The DSE block integrates localized perception with direction-aware context aggregation to help capture long-range spatial dependencies and local details. On this basis, the LaSEA module mitigates feature degradation via cross-scale feature extraction and random pooling sampling strategies, enhancing discriminative features and suppressing noise. Extensive experiments show that DCCS-Det achieves state-of-the-art detection accuracy with competitive efficiency across multiple datasets. Ablation studies further validate the contributions of DSE and LaSEA in improving target perception and feature representation under complex scenarios. Code is available at https://github.com/ML202010/DCCS-Det

Problem

• Infrared small target detection
• local-global feature modeling
• feature redundancy
• semantic dilution
• target-background discrimination

Innovation

• Dual-stream Saliency Enhancement
• Latent-aware Semantic Extraction and Aggregation
• Directional Context
• Cross-Scale Feature Extraction
• Infrared Small Target Detection