Custom Object Detection via Multi-Camera Self-Supervised Learning
arXiv:2102.03442
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.
arXiv comment7 pages, 12 figures
References in corpus (5)
- Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks
- YOLOv3: An Incremental Improvement
- MMDetection: Open MMLab Detection Toolbox and Benchmark
- There Are Many Consistent Explanations of Unlabeled Data: Why You Should Average
- Fast Visual Object Tracking with Rotated Bounding Boxes