YOLO: You Only Look 10647 Times

Christian Limberg, Andrew Melnik, Helge Ritter, Helmut Prendinger

2023

Abstract

In this work, we explore the You Only Look Once (YOLO) single-stage object detection architecture and compare it to the simultaneous classification of 10647 fixed region proposals. We use two different approaches to demonstrate that each of YOLO’s grid cells is attentive to a specific sub-region of previous layers. This finding makes YOLO’s method comparable to local region proposals. Such insight reduces the conceptual gap between YOLO-like single-stage object detection models, R-CNN-like two-stage region proposal based models, and ResNet-like image classification models. For this work, we created interactive exploration tools for a better visual understanding of the YOLO information processing streams: https://limchr.github.io/yolo_visu

Paper Citation

in Harvard Style

Limberg C., Melnik A., Ritter H. and Prendinger H. (2023). YOLO: You Only Look 10647 Times. In Proceedings of the 18th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications (VISIGRAPP 2023) - Volume 5: VISAPP; ISBN 978-989-758-634-7, SciTePress, pages 153-160. DOI: 10.5220/0011677300003417

in Bibtex Style

@conference{visapp23,
author={Christian Limberg and Andrew Melnik and Helge Ritter and Helmut Prendinger},
title={YOLO: You Only Look 10647 Times},
booktitle={Proceedings of the 18th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications (VISIGRAPP 2023) - Volume 5: VISAPP},
year={2023},
pages={153-160},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0011677300003417},
isbn={978-989-758-634-7},
}

in EndNote Style

TY - CONF

JO - Proceedings of the 18th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications (VISIGRAPP 2023) - Volume 5: VISAPP
TI - YOLO: You Only Look 10647 Times
SN - 978-989-758-634-7
AU - Limberg C.
AU - Melnik A.
AU - Ritter H.
AU - Prendinger H.
PY - 2023
SP - 153
EP - 160
DO - 10.5220/0011677300003417
PB - SciTePress