Paper published in a book (Scientific congresses and symposiums)
Semi-Supervised Training to Improve Player and Ball Detection in Soccer
Vandeghen, Renaud; Cioppa, Anthony; Van Droogenbroeck, Marc
2022In IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW)
Peer reviewed
 

Files


Full Text
Vandeghen2022SemiSupervised.pdf
Author postprint (3.95 MB)
Download

All documents in ORBi are protected by a user license.

Send to



Details



Keywords :
Computer vision; Machine learning; Semi-supervised learning; Soccer; Detection; Ball detection; Player detection; Human detection; SoccerNet-v3
Abstract :
[en] Accurate player and ball detection has become increasingly important in recent years for sport analytics. As most state-of-the-art methods rely on training deep learning networks in a supervised fashion, they require huge amounts of annotated data, which are rarely available. In this paper, we present a novel generic semi-supervised method to train a network based on a labeled image dataset by leveraging a large unlabeled dataset of soccer broadcast videos. More precisely, we design a teacher-student approach in which the teacher produces surrogate annotations on the unlabeled data to be used later for training a student which has the same architecture as the teacher. Furthermore, we introduce three training loss parametrizations that allow the student to doubt the predictions of the teacher during training depending on the proposal confidence score. We show that including unlabeled data in the training process allows to substantially improve the performances of the detection network trained only on the labeled data. Finally, we provide a thorough performance study including different proportions of labeled and unlabeled data, and establish the first benchmark on the new SoccerNet-v3 detection task, with an mAP of 52.3%. Our code is available at https://github.com/rvandeghen/SST .
Research Center/Unit :
Montefiore Institute - Montefiore Institute of Electrical Engineering and Computer Science - ULiège
Telim
Disciplines :
Computer science
Author, co-author :
Vandeghen, Renaud  ;  Université de Liège - ULiège > Département d'électricité, électronique et informatique (Institut Montefiore) > Télécommunications
Cioppa, Anthony   ;  Université de Liège - ULiège > Département d'électricité, électronique et informatique (Institut Montefiore) > Télécommunications
Van Droogenbroeck, Marc  ;  Université de Liège - ULiège > Département d'électricité, électronique et informatique (Institut Montefiore) > Télécommunications
 These authors have contributed equally to this work.
Language :
English
Title :
Semi-Supervised Training to Improve Player and Ball Detection in Soccer
Publication date :
June 2022
Event name :
8th International Workshop on Computer Vision in Sports (CVsports)
Event organizer :
IEEE
Event place :
New Orleans, United States - Louisiana
Event date :
du 19 juin 2022 au 20 juin 2022
Audience :
International
Main work title :
IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW)
Publisher :
IEEE
Pages :
3480-3489
Peer reviewed :
Peer reviewed
Available on ORBi :
since 15 April 2022

Statistics


Number of views
113 (47 by ULiège)
Number of downloads
52 (7 by ULiège)

Scopus citations®
 
26
Scopus citations®
without self-citations
16
OpenCitations
 
0
OpenAlex citations
 
23

Bibliography


Similar publications



Contact ORBi