Pith

open record

sign in

arxiv: 2102.03442 · v1 · pith:JT36EU2P · submitted 2021-02-05 · cs.CV · cs.AI

Custom Object Detection via Multi-Camera Self-Supervised Learning

Reviewed by Pith T0 review T1 audit T2 compute T3 formal T4 kernel pith:JT36EU2Precord.jsonopen to challenge →

classification cs.CV cs.AI
keywords detectionmcsslobjectcustomlearningmodelmulti-cameranetworks
0
0 comments X
read the original 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.

This paper has not been read by Pith yet.

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.