ARTHuS: Adaptive Real-Time Human Segmentation in Sports Through Online Distillation

Anthony Cioppa, Adrien Deliege, Maxime Istasse, Christophe De Vleeschouwer, Marc Van Droogenbroeck; The IEEE Conference on Computer Vision and Pattern Recognition (CVPR) Workshops, 2019, pp. 0-0

Abstract


Semantic segmentation can be regarded as a useful tool for global scene understanding in many areas, including sports, but has inherent difficulties, such as the need for pixel-wise annotated training data and the absence of well-performing real-time universal algorithms. To alleviate these issues, we sacrifice universality by developing a general method, named ARTHuS, that produces adaptive real-time match-specific networks for human segmentation in sports videos, without requiring any manual annotation. This is done by an online knowledge distillation process, in which a fast student network is trained to mimic the output of an existing slow but effective universal teacher network, while being periodically updated to adjust to the latest play conditions. As a result, ARTHuS allows to build highly effective real-time human segmentation networks that evolve through the match and that sometimes outperform their teacher. The usefulness of producing adaptive match-specific networks and their excellent performances are demonstrated quantitatively and qualitatively for soccer and basketball matches.

Related Material


[pdf] [supp]
[bibtex]
@InProceedings{Cioppa_2019_CVPR_Workshops,
author = {Cioppa, Anthony and Deliege, Adrien and Istasse, Maxime and De Vleeschouwer, Christophe and Van Droogenbroeck, Marc},
title = {ARTHuS: Adaptive Real-Time Human Segmentation in Sports Through Online Distillation},
booktitle = {The IEEE Conference on Computer Vision and Pattern Recognition (CVPR) Workshops},
month = {June},
year = {2019}
}