English

Custom Object Detection via Multi-Camera Self-Supervised Learning

Computer Vision and Pattern Recognition 2021-02-09 v1 Artificial Intelligence

Abstract

This paper proposes MCSSL, a self-supervised learning approach for building custom object detection models in multi-camera networks. MCSSL associates bounding boxes between cameras with overlapping fields of view by leveraging epipolar geometry and state-of-the-art tracking and reID algorithms, and prudently generates two sets of pseudo-labels to fine-tune backbone and detection networks respectively in an object detection model. To train effectively on pseudo-labels,a powerful reID-like pretext task with consistency loss is constructed for model customization. Our evaluation shows that compared with legacy selftraining methods, MCSSL improves average mAP by 5.44% and 6.76% on WildTrack and CityFlow dataset, respectively.

Keywords

Cite

@article{arxiv.2102.03442,
  title  = {Custom Object Detection via Multi-Camera Self-Supervised Learning},
  author = {Yan Lu and Yuanchao Shu},
  journal= {arXiv preprint arXiv:2102.03442},
  year   = {2021}
}

Comments

7 pages, 12 figures

R2 v1 2026-06-23T22:53:27.836Z