$\textit{A Contrario}$ Paradigm for YOLO-based Infrared Small Target Detection
This work addresses the challenge of infrared small target detection for computer vision applications, representing an incremental improvement by adapting an existing statistical method to enhance a standard object detection network.
The paper tackles the problem of detecting small infrared targets in noisy backgrounds by integrating an a contrario decision criterion into YOLOv7-tiny training, resulting in reduced false alarms and bridging the performance gap with segmentation methods while increasing robustness in few-shot settings.
Detecting small to tiny targets in infrared images is a challenging task in computer vision, especially when it comes to differentiating these targets from noisy or textured backgrounds. Traditional object detection methods such as YOLO struggle to detect tiny objects compared to segmentation neural networks, resulting in weaker performance when detecting small targets. To reduce the number of false alarms while maintaining a high detection rate, we introduce an $\textit{a contrario}$ decision criterion into the training of a YOLO detector. The latter takes advantage of the $\textit{unexpectedness}$ of small targets to discriminate them from complex backgrounds. Adding this statistical criterion to a YOLOv7-tiny bridges the performance gap between state-of-the-art segmentation methods for infrared small target detection and object detection networks. It also significantly increases the robustness of YOLO towards few-shot settings.