Ctrl K

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

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

1
mention
6
contributors

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.

Logo of Data underlying the publication/thesis chapter: FlexConv: Continuous Kernel Convolutions with Differentiable Kernel Sizes
Keywords
computer vision
Convolutional Neural Network
kernel size
long-term dependencies
receptive field
Programming languages
License
  • CC-BY-4.0
</>Source code
Packages

Reference papers

Mentions

Contributors

DR
David Romero
EB
Erik Bekkers
JT
Jakub Tomczak
MH
Mark Hoogendoorn

Member of community

4TU