Anomaly-Aware YOLO: A Frugal yet Robust Approach to Infrared Small Target Detection
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , |
|---|---|
| Format: | Preprint |
| Publié: |
2025
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866915805137993728 |
|---|---|
| author | Ciocarlan, Alina Hégarat-Mascle, Sylvie Le Lefebvre, Sidonie |
| author_facet | Ciocarlan, Alina Hégarat-Mascle, Sylvie Le Lefebvre, Sidonie |
| contents | Infrared Small Target Detection (IRSTD) is a challenging task in defense applications, where complex backgrounds and tiny target sizes often result in numerous false alarms using conventional object detectors. To overcome this limitation, we propose Anomaly-Aware YOLO (AA-YOLO), which integrates a statistical anomaly detection test into its detection head. By treating small targets as unexpected patterns against the background, AA-YOLO effectively controls the false alarm rate. Our approach not only achieves competitive performance on several IRSTD benchmarks, but also demonstrates remarkable robustness in scenarios with limited training data, noise, and domain shifts. Furthermore, since only the detection head is modified, our design is highly generic and has been successfully applied across various YOLO backbones, including lightweight models. It also provides promising results when integrated into an instance segmentation YOLO. This versatility makes AA-YOLO an attractive solution for real-world deployments where resources are constrained. The code will be publicly released. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2510_04741 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Anomaly-Aware YOLO: A Frugal yet Robust Approach to Infrared Small Target Detection Ciocarlan, Alina Hégarat-Mascle, Sylvie Le Lefebvre, Sidonie Computer Vision and Pattern Recognition Infrared Small Target Detection (IRSTD) is a challenging task in defense applications, where complex backgrounds and tiny target sizes often result in numerous false alarms using conventional object detectors. To overcome this limitation, we propose Anomaly-Aware YOLO (AA-YOLO), which integrates a statistical anomaly detection test into its detection head. By treating small targets as unexpected patterns against the background, AA-YOLO effectively controls the false alarm rate. Our approach not only achieves competitive performance on several IRSTD benchmarks, but also demonstrates remarkable robustness in scenarios with limited training data, noise, and domain shifts. Furthermore, since only the detection head is modified, our design is highly generic and has been successfully applied across various YOLO backbones, including lightweight models. It also provides promising results when integrated into an instance segmentation YOLO. This versatility makes AA-YOLO an attractive solution for real-world deployments where resources are constrained. The code will be publicly released. |
| title | Anomaly-Aware YOLO: A Frugal yet Robust Approach to Infrared Small Target Detection |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2510.04741 |