NS-FPN: Improving Infrared Small Target Detection and Segmentation from Noise Suppression Perspective

2025-08-09

AI Summary

Infrared small target detection and segmentation (IRSTDS) suffers from low signal-to-noise ratio, ambiguous target morphology, and severe background clutter, leading to high false alarm rates. To address these challenges, we propose NS-FPN—a noise-suppression-guided feature pyramid network—that pioneers a frequency-domain noise modeling perspective to decouple feature enhancement from noise suppression. Specifically, we design a Low-frequency-guided Feature Purification (LFP) module to suppress background clutter and introduce a Spiral-aware Feature Sampling (SFS) mechanism to strengthen multi-scale responses of small targets. The architecture is lightweight and plug-and-play. Evaluated on mainstream IRSTDS benchmarks, NS-FPN achieves significantly lower false alarm rates and outperforms state-of-the-art CNN- and Transformer-based methods in both detection and segmentation accuracy, while maintaining high computational efficiency and framework compatibility.

Technology Category

• Computer Vision: Other Foundations of Computer Vision
• Natural Language Processing: Fact-Checking / Misinformation Detection (NLP Focus)
• Machine Learning: Feature Construction/Reformulation

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
• Security and Privacy: Large-scale security measurements

Abstract

Infrared small target detection and segmentation (IRSTDS) is a critical yet challenging task in defense and civilian applications, owing to the dim, shapeless appearance of targets and severe background clutter. Recent CNN-based methods have achieved promising target perception results, but they only focus on enhancing feature representation to offset the impact of noise, which results in the increased false alarms problem. In this paper, through analyzing the problem from the frequency domain, we pioneer in improving performance from noise suppression perspective and propose a novel noise-suppression feature pyramid network (NS-FPN), which integrates a low-frequency guided feature purification (LFP) module and a spiral-aware feature sampling (SFS) module into the original FPN structure. The LFP module suppresses the noise features by purifying high-frequency components to achieve feature enhancement devoid of noise interference, while the SFS module further adopts spiral sampling to fuse target-relevant features in feature fusion process. Our NS-FPN is designed to be lightweight yet effective and can be easily plugged into existing IRSTDS frameworks. Extensive experiments on the public IRSTDS datasets demonstrate that our method significantly reduces false alarms and achieves superior performance on IRSTDS tasks.

Problem

• Improving infrared small target detection and segmentation
• Reducing false alarms in target detection
• Suppressing noise in feature enhancement

Innovation

• Low-frequency guided feature purification module
• Spiral-aware feature sampling module
• Lightweight noise-suppression feature pyramid network