loading
Papers Papers/2022 Papers Papers/2022

Research.Publish.Connect.

Paper

Paper Unlock

Authors: Yuqi Zhang ; Yuyang Xie ; Linfeng Luo and Fengming Cao

Affiliation: Pingan International Smart City Technologies Ltd., Shenzhen, China

Keyword(s): Deformable Convolution, Object Detection, Visualization.

Abstract: The deformable convolution improves the performance by a large margin across various tasks in computer vision. The detailed analysis of the deformable convolution attracts less attention than the application of it. To strengthen the understanding of the deformable convolution, the offset fields of the deformable convolution in object detectors are visualized with proposed visualizing methods. After projecting the offset fields to the feature map coordinates, we find that the displacement condenses the features of each object to the object center and it learns to segment objects even without segmentation annotations. Meanwhile, projecting the offset fields to the kernel coordinates demonstrates that the displacement inside each kernel is able to predict the size of the object on it. The two findings indicate the offset field learns to predict the location and the size of the object, which are crucial in understanding the image. The visualization in this work explicitly shows the power of the deformable convolution by decoding the information in the offset fields. The ablation studies of the two projections of the offset fields reveal that the projection in the kernel viewpoint contributes mostly in current object detectors. (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 3.145.156.46

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:
Zhang, Y.; Xie, Y.; Luo, L. and Cao, F. (2021). Revisiting the Deformable Convolution by Visualization. In Proceedings of the 10th International Conference on Pattern Recognition Applications and Methods - ICPRAM; ISBN 978-989-758-486-2; ISSN 2184-4313, SciTePress, pages 190-195. DOI: 10.5220/0010200801900195

@conference{icpram21,
author={Yuqi Zhang. and Yuyang Xie. and Linfeng Luo. and Fengming Cao.},
title={Revisiting the Deformable Convolution by Visualization},
booktitle={Proceedings of the 10th International Conference on Pattern Recognition Applications and Methods - ICPRAM},
year={2021},
pages={190-195},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0010200801900195},
isbn={978-989-758-486-2},
issn={2184-4313},
}

TY - CONF

JO - Proceedings of the 10th International Conference on Pattern Recognition Applications and Methods - ICPRAM
TI - Revisiting the Deformable Convolution by Visualization
SN - 978-989-758-486-2
IS - 2184-4313
AU - Zhang, Y.
AU - Xie, Y.
AU - Luo, L.
AU - Cao, F.
PY - 2021
SP - 190
EP - 195
DO - 10.5220/0010200801900195
PB - SciTePress

- Science and Technology Publications, Lda.
RESOURCES

Proceedings

Papers

Authors

Ontology

CONTACTS

Science and Technology Publications, Lda
Avenida de S. Francisco Xavier, Lote 7 Cv. C,
2900-616 Setúbal, Portugal.

Phone: +351 265 520 185 (National fixed network call)
Fax: +351 265 520 186
Email: info@scitepress.org

EXTERNAL LINKS

PRIMORIS

INSTICC

SCITEVENTS

CROSSREF

PROCEEDINGS SUBMITTED FOR INDEXATION BY:

dblp

Ei Compendex

SCOPUS

Semantic Scholar

Google Scholar

Microsoft Academic