Infrared small target detection (IRSTD) is critical for defense and surveillance but remains challenging due to (1) target loss from minimal features, (2) false alarms in cluttered environments, (3) missed detections from low saliency, and (4) high computational costs. To address these issues, we propose TY-RIST, an optimized YOLOv12n architecture that integrates (1) a stride-aware backbone with fine-grained receptive fields, (2) a high-resolution detection head, (3) cascaded coordinate attention blocks, and (4) a branch pruning strategy that reduces computational cost by about 25.5% while marginally improving accuracy and enabling real-time inference. We also incorporate the Normalized Gaussian Wasserstein Distance (NWD) to enhance regression stability. Extensive experiments on four benchmarks and across 20 different models demonstrate state-of-the-art performance, improving mAP at 0.5 IoU by +7.9%, Precision by +3%, and Recall by +10.2%, while achieving up to 123 FPS on a single GPU. Cross-dataset validation on a fifth dataset further confirms strong generalization capability. Additional results and resources are available at https://www.github.com/moured/TY-RIST
@article{arxiv.2509.22909,
title = {TY-RIST: Tactical YOLO Tricks for Real-time Infrared Small Target Detection},
author = {Abdulkarim Atrash and Omar Moured and Yufan Chen and Jiaming Zhang and Seyda Ertekin and Omur Ugur},
journal= {arXiv preprint arXiv:2509.22909},
year = {2025}
}
Comments
Acctepted at the ICCV 2025 MIRA workshop, 11 pages, 7 figures