arXiv:2512.09497v1 Announce Type: new 
Abstract: Recently, infrared small target detection has attracted extensive attention. However, due to the small size and the lack of intrinsic features of infrared small targets, the existing methods generally have the problem of inaccurate edge positioning and the target is easily submerged by the background. Therefore, we propose an innovative gradient-guided learning network (GGL-Net). Specifically, we are the first to explore the introduction of gradient magnitude images into the deep learning-based infrared small target detection method, which is conducive to emphasizing the edge details and alleviating the problem of inaccurate edge positioning of small targets. On this basis, we propose a novel dual-branch feature extraction network that utilizes the proposed gradient supplementary module (GSM) to encode raw gradient information into deeper network layers and embeds attention mechanisms reasonably to enhance feature extraction ability. In addition, we construct a two-way guidance fusion module (TGFM), which fully considers the characteristics of feature maps at different levels. It can facilitate the effective fusion of multi-scale feature maps and extract richer semantic information and detailed information through reasonable two-way guidance. Extensive experiments prove that GGL-Net has achieves state-of-the-art results on the public real NUAA-SIRST dataset and the public synthetic NUDT-SIRST dataset. Our code has been integrated into https://github.com/YuChuang1205/MSDA-Net

تم اقتراح شبكة تعلم جديدة موجهة بواسطة التدرج (GGL-Net) لاكتشاف الأهداف الصغيرة في الأشعة تحت الحمراء، حيث تعالج التحديات مثل تحديد حواف غير دقيق والتداخل مع الخلفية. تتضمن هذه الطريقة المبتكرة إدخال صور مقدار التدرج في أساليب التعلم العميق لتعزيز التعرف على تفاصيل الحواف وتحسين دقة الاكتشاف.

Se ha propuesto una nueva red de aprendizaje guiada por gradientes (GGL-Net) para la detección de pequeños objetivos infrarrojos, abordando desafíos como la posición inexacta de los bordes y la interferencia del fondo. Este enfoque innovador incorpora imágenes de magnitud de gradiente en métodos de aprendizaje profundo para mejorar el reconocimiento de detalles en los bordes y la precisión de la detección.

Un nouveau réseau d'apprentissage guidé par gradient (GGL-Net) a été proposé pour la détection de petites cibles infrarouges, répondant à des défis tels que le positionnement inexact des bords et l'interférence de l'arrière-plan. Cette approche innovante intègre des images de magnitude de gradient dans des méthodes d'apprentissage profond pour améliorer la reconnaissance des détails des bords et la précision de la détection.

A new gradient-guided learning network (GGL-Net) has been proposed for infrared small target detection, addressing challenges such as inaccurate edge positioning and background interference. This innovative approach incorporates gradient magnitude images into deep learning methods to enhance edge detail recognition and improve detection accuracy.

Gradient-Guided Learning Network for Infrared Small Target Detection

Was this article worth reading? Share it

LucidQuery AI

WasItAI

Blunge

Attentive AI

Lenso.ai

GPTHumanizer

Ready to build your own newsroom?