Leveraging Language Prior for Infrared Small Target Detection

TL;DR

This paper introduces a multimodal infrared small target detection framework that incorporates language priors and leverages GPT-4 vision models to improve detection accuracy, addressing dataset limitations and enhancing performance over existing methods.

Contribution

It proposes a novel multimodal IRSTD approach using language priors and creates a new dataset combining image and text modalities for small target detection.

Findings

Significant improvements in IoU, nIoU, Pd, and Fa metrics over state-of-the-art methods.

Effective use of GPT-4 vision model for generating text-based target location descriptions.

Validation through extensive experiments and ablation studies.

Abstract

IRSTD (InfraRed Small Target Detection) detects small targets in infrared blurry backgrounds and is essential for various applications. The detection task is challenging due to the small size of the targets and their sparse distribution in infrared small target datasets. Although existing IRSTD methods and datasets have led to significant advancements, they are limited by their reliance solely on the image modality. Recent advances in deep learning and large vision-language models have shown remarkable performance in various visual recognition tasks. In this work, we propose a novel multimodal IRSTD framework that incorporates language priors to guide small target detection. We leverage language-guided attention weights derived from the language prior to enhance the model's ability for IRSTD, presenting a novel approach that combines textual information with image data to improve IRSTD capabilities. Utilizing the state-of-the-art GPT-4 vision model, we generate text descriptions that provide the locations of small targets in infrared images, employing careful prompt engineering to ensure improved accuracy. Due to the absence of multimodal IR datasets, existing IRSTD methods rely solely on image data. To address this shortcoming, we have curated a multimodal infrared dataset that includes both image and text modalities for small target detection, expanding upon the popular IRSTD-1k and NUDT-SIRST datasets. We validate the effectiveness of our approach through extensive experiments and comprehensive ablation studies. The results demonstrate significant improvements over the state-of-the-art method, with relative percentage differences of 9.74%, 13.02%, 1.25%, and 67.87% in IoU, nIoU, Pd, and Fa on the NUAA-SIRST subset, and 4.41%, 2.04%, 2.01%, and 113.43% on the IRSTD-1k subset of the LangIR dataset, respectively.