Rethinking Generalizable Infrared Small Target Detection: A Real-scene Benchmark and Cross-view Representation Learning

2025-04-23

AI Summary

To address the poor generalization of infrared small target detection (ISTD) across sensors, environments, and noisy conditions, this paper proposes a domain-adaptive framework. Methodologically, it introduces cross-view channel alignment (CCA) — the first of its kind — coupled with a Top-K feature fusion mechanism to achieve robust multi-view feature alignment; designs a noise-guided representation learning strategy to enhance model robustness against imaging noise; and constructs RealScene-ISTD, the first benchmark dataset dedicated to realistic-scenario generalization evaluation. Extensive experiments demonstrate that the proposed method consistently outperforms state-of-the-art approaches in detection probability (Pd), false alarm rate (Fa), and intersection-over-union (IoU). Notably, it achieves significant gains in cross-domain generalization and resilience to noise interference, validating its effectiveness for practical deployment under diverse and challenging real-world conditions.

Technology Category

• Intelligent Robots: Multimodal Perception & Sensor Fusion
• Machine Learning: Transfer, Domain Adaptation, Multi-Task Learning
• Computer Vision: Adversarial Attacks & Robustness

Application Category

• Search and Retrieval-Augmented AI: Vertical and domain-specific search
• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications
• Web Mining and Content Analysis: Robustness and generalizability of Web mining methods

Abstract

Infrared small target detection (ISTD) is highly sensitive to sensor type, observation conditions, and the intrinsic properties of the target. These factors can introduce substantial variations in the distribution of acquired infrared image data, a phenomenon known as domain shift. Such distribution discrepancies significantly hinder the generalization capability of ISTD models across diverse scenarios. To tackle this challenge, this paper introduces an ISTD framework enhanced by domain adaptation. To alleviate distribution shift between datasets and achieve cross-sample alignment, we introduce Cross-view Channel Alignment (CCA). Additionally, we propose the Cross-view Top-K Fusion strategy, which integrates target information with diverse background features, enhancing the model' s ability to extract critical data characteristics. To further mitigate the impact of noise on ISTD, we develop a Noise-guided Representation learning strategy. This approach enables the model to learn more noise-resistant feature representations, to improve its generalization capability across diverse noisy domains. Finally, we develop a dedicated infrared small target dataset, RealScene-ISTD. Compared to state-of-the-art methods, our approach demonstrates superior performance in terms of detection probability (Pd), false alarm rate (Fa), and intersection over union (IoU). The code is available at: https://github.com/luy0222/RealScene-ISTD.

Problem

• Address domain shift in infrared small target detection
• Improve cross-scenario generalization of detection models
• Reduce noise impact on target detection accuracy

Innovation

• Cross-view Channel Alignment for domain adaptation
• Cross-view Top-K Fusion for feature integration
• Noise-guided Representation learning for robustness