Data underlying the publication/thesis chapter: FlexConv: Continuous Kernel Convolutions with Differentiable Kernel Sizes

Author name

doi:10.4121/64c5aba1-e619-42c9-bf39-57fe84f2e7e7

Ctrl K

Software Projects Organisations Communities News

Ctrl K

Limited functionality: Your browser does not support JavaScript.

Data underlying the publication/thesis chapter: FlexConv: Continuous Kernel Convolutions with Differentiable Kernel Sizes

mention

contributors

Get started

26 commitsLast commit ≈ 36 months ago

Description

ICLR article and thesis chapter. This article contributes a novel convolutional operator that can learn to modulate its kernel size, and can be used to perform scale generalization.

Keywords

computer vision

Convolutional Neural Network

kernel size

long-term dependencies

receptive field

Programming languages

Python 69%
Jupyter Notebook 18%
Markdown 7%
Other 4%
YAML 2%

License

CC-BY-4.0

</>Source code

Packages

Reference papers

1.
Author(s): David W. Romero, Robert-Jan Bruintjes, Jakub M. Tomczak, Erik J. Bekkers, Mark Hoogendoorn, Jan C. van Gemert
Published by arXiv in 2021
10.48550/arxiv.2110.08059

Mentions

1.
Author(s): Hamid Mousavi, Mohammad Loni, Mina Alibeigi, Masoud Daneshtalab
Published in ACM Transactions on Embedded Computing Systems by Association for Computing Machinery (ACM) in 2023, page: 1-21
10.1145/3609385

Contributors

David Romero

Erik Bekkers

Jakub Tomczak

JvG

Jan van Gemert

0000-0002-6913-0482

Mark Hoogendoorn

Robert-Jan Bruintjes

0000-0002-9798-0214

Member of community

Data underlying the publication/thesis chapter: FlexConv: Continuous Kernel Convolutions with Differentiable Kernel Sizes

Description

Reference papers

Other1

Mentions

Journal articles1

Contributors

Member of community