loading
Papers Papers/2022 Papers Papers/2022

Research.Publish.Connect.

Paper

Paper Unlock

Authors: Tobias Scheck ; Ana Perez Grassi and Gangolf Hirtz

Affiliation: Faculty of Electrical Engineering and Information Technology, Chemnitz University of Technology, Germany

Keyword(s): Unsupervised Domain Adaptation, Synthetic Images, CenterNet, Anchorless/Keypoint-based Detectors, Object Detection.

Abstract: Synthetic images are one of the most promising solutions to avoid high costs associated with generating annotated datasets to train supervised convolutional neural networks (CNN). However, to allow networks to generalize knowledge from synthetic to real images, domain adaptation methods are necessary. This paper implements unsupervised domain adaptation (UDA) methods on an anchorless object detector. Given their good performance, anchorless detectors are increasingly attracting attention in the field of object detection. While their results are comparable to the well-established anchor-based methods, anchorless detectors are considerably faster. In our work, we use CenterNet, one of the most recent anchorless architectures, for a domain adaptation problem involving synthetic images. Taking advantage of the architecture of anchorless detectors, we propose to adjust two UDA methods, viz., entropy minimization and maximum squares loss, originally developed for segmentation, to object de tection. Our results show that the proposed UDA methods can increase the mAP from 61% to 69% with respect to direct transfer on the considered anchorless detector. The code is available: https://github.com/scheckmedia/centernet-uda. (More)

CC BY-NC-ND 4.0

Sign In Guest: Register as new SciTePress user now for free.

Sign In SciTePress user: please login.

PDF ImageMy Papers

You are not signed in, therefore limits apply to your IP address 54.157.61.194

In the current month:
Recent papers: 100 available of 100 total
2+ years older papers: 200 available of 200 total

Paper citation in several formats:
Scheck, T.; Grassi, A. and Hirtz, G. (2021). Unsupervised Domain Adaptation from Synthetic to Real Images for Anchorless Object Detection. In Proceedings of the 16th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications (VISIGRAPP 2021) - Volume 5: VISAPP; ISBN 978-989-758-488-6; ISSN 2184-4321, SciTePress, pages 319-327. DOI: 10.5220/0010202503190327

@conference{visapp21,
author={Tobias Scheck. and Ana Perez Grassi. and Gangolf Hirtz.},
title={Unsupervised Domain Adaptation from Synthetic to Real Images for Anchorless Object Detection},
booktitle={Proceedings of the 16th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications (VISIGRAPP 2021) - Volume 5: VISAPP},
year={2021},
pages={319-327},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0010202503190327},
isbn={978-989-758-488-6},
issn={2184-4321},
}

TY - CONF

JO - Proceedings of the 16th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications (VISIGRAPP 2021) - Volume 5: VISAPP
TI - Unsupervised Domain Adaptation from Synthetic to Real Images for Anchorless Object Detection
SN - 978-989-758-488-6
IS - 2184-4321
AU - Scheck, T.
AU - Grassi, A.
AU - Hirtz, G.
PY - 2021
SP - 319
EP - 327
DO - 10.5220/0010202503190327
PB - SciTePress