The DOI displayed above is for this specific version of this dataset, which is currently the latest. Newer versions may be published in the future. For a link that will always point to the latest version, please use
DOI: 10.4121/64c5aba1-e619-42c9-bf39-57fe84f2e7e7

Romero, David; Bruintjes, Robert-Jan; Tomczak, Jakub; Bekkers, Erik; Hoogendoorn, Mark et. al. (2025): Data underlying the publication/thesis chapter: FlexConv: Continuous Kernel Convolutions with Differentiable Kernel Sizes. Version 1. 4TU.ResearchData. software. https://doi.org/10.4121/64c5aba1-e619-42c9-bf39-57fe84f2e7e7.v1

Categories

• Artificial Intelligence and Image Processing
• Information and Computing Sciences

Keywords

computer vision Convolutional Neural Network kernel size long-term dependencies receptive field

Licence

CC BY 4.0

Interoperability

• RO-Crate Metadata

Export as...

RefWorks BibTeX Reference Manager Endnote DataCite NLM DC CFF

by David Romero, Robert-Jan Bruintjes , Jakub Tomczak, Erik Bekkers, Mark Hoogendoorn, Jan van Gemert

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.

History

• 2025-09-09 first online, published, posted

Publisher

4TU.ResearchData

Format

GitHub repository containing Python files.

Associated peer-reviewed publication

FlexConv: Continuous Kernel Convolutions with Differentiable Kernel Sizes

References

• https://arxiv.org/abs/2110.08059

Organizations

TU Delft, Faculty of Electrical Engineering, Mathematics and Computer Science, Department of Intelligent Systems, Computer Vision Lab