Robust infrared small target detection using self-supervised and a contrario paradigms

TL;DR

This paper presents a novel IR small target detection method combining a contrario paradigm with self-supervised learning, significantly improving detection accuracy and reducing false alarms in complex infrared images.

Contribution

It introduces a combined approach of a contrario criterion and SSL techniques into YOLO for enhanced small target detection in infrared images, addressing data scarcity and false alarm issues.

Findings

Instance discrimination surpasses masked image modeling in effectiveness.

Combining a contrario and SSL paradigms improves detection performance.

Outperforms state-of-the-art segmentation methods in frugal settings.

Abstract

Detecting small targets in infrared images poses significant challenges in defense applications due to the presence of complex backgrounds and the small size of the targets. Traditional object detection methods often struggle to balance high detection rates with low false alarm rates, especially when dealing with small objects. In this paper, we introduce a novel approach that combines a contrario paradigm with Self-Supervised Learning (SSL) to improve Infrared Small Target Detection (IRSTD). On the one hand, the integration of an a contrario criterion into a YOLO detection head enhances feature map responses for small and unexpected objects while effectively controlling false alarms. On the other hand, we explore SSL techniques to overcome the challenges of limited annotated data, common in IRSTD tasks. Specifically, we benchmark several representative SSL strategies for their effectiveness in improving small object detection performance. Our findings show that instance discrimination methods outperform masked image modeling strategies when applied to YOLO-based small object detection. Moreover, the combination of the a contrario and SSL paradigms leads to significant performance improvements, narrowing the gap with state-of-the-art segmentation methods and even outperforming them in frugal settings. This two-pronged approach offers a robust solution for improving IRSTD performance, particularly under challenging conditions.