English

YOLO11-JDE: Fast and Accurate Multi-Object Tracking with Self-Supervised Re-ID

Computer Vision and Pattern Recognition 2025-05-28 v1 Artificial Intelligence

Abstract

We introduce YOLO11-JDE, a fast and accurate multi-object tracking (MOT) solution that combines real-time object detection with self-supervised Re-Identification (Re-ID). By incorporating a dedicated Re-ID branch into YOLO11s, our model performs Joint Detection and Embedding (JDE), generating appearance features for each detection. The Re-ID branch is trained in a fully self-supervised setting while simultaneously training for detection, eliminating the need for costly identity-labeled datasets. The triplet loss, with hard positive and semi-hard negative mining strategies, is used for learning discriminative embeddings. Data association is enhanced with a custom tracking implementation that successfully integrates motion, appearance, and location cues. YOLO11-JDE achieves competitive results on MOT17 and MOT20 benchmarks, surpassing existing JDE methods in terms of FPS and using up to ten times fewer parameters. Thus, making our method a highly attractive solution for real-world applications.

Keywords

Cite

@article{arxiv.2501.13710,
  title  = {YOLO11-JDE: Fast and Accurate Multi-Object Tracking with Self-Supervised Re-ID},
  author = {Iñaki Erregue and Kamal Nasrollahi and Sergio Escalera},
  journal= {arXiv preprint arXiv:2501.13710},
  year   = {2025}
}

Comments

This paper has been accepted to the 5th Workshop on Real-World Surveillance: Applications and Challenges (WACV 2025)

R2 v1 2026-06-28T21:14:54.079Z