Dual-Granularity Semantic Prompting for Language Guidance Infrared Small Target Detection

TL;DR

This paper introduces DGSPNet, a novel language prompt-driven framework for infrared small target detection that leverages dual-granularity semantic prompts and attention mechanisms to improve accuracy without manual annotations.

Contribution

The paper proposes a new end-to-end framework integrating dual-granularity semantic prompts and attention mechanisms, enabling effective language-guided infrared small target detection without manual annotations.

Findings

Significantly improves detection accuracy on benchmark datasets.

Achieves state-of-the-art performance in infrared small target detection.

Effectively leverages language prompts for enhanced feature sensitivity.

Abstract

Infrared small target detection remains challenging due to limited feature representation and severe background interference, resulting in sub-optimal performance. While recent CLIP-inspired methods attempt to leverage textual guidance for detection, they are hindered by inaccurate text descriptions and reliance on manual annotations. To overcome these limitations, we propose DGSPNet, an end-to-end language prompt-driven framework. Our approach integrates dual-granularity semantic prompts: coarse-grained textual priors (e.g., 'infrared image', 'small target') and fine-grained personalized semantic descriptions derived through visual-to-textual mapping within the image space. This design not only facilitates learning fine-grained semantic information but also can inherently leverage language prompts during inference without relying on any annotation requirements. By fully leveraging the precision and conciseness of text descriptions, we further introduce a text-guide channel attention (TGCA) mechanism and text-guide spatial attention (TGSA) mechanism that enhances the model's sensitivity to potential targets across both low- and high-level feature spaces. Extensive experiments demonstrate that our method significantly improves detection accuracy and achieves state-of-the-art performance on three benchmark datasets.