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: 10.4121/471ed486-bc86-40de-9e1d-9446cd6ec5aa

Bruintjes, Robert-Jan; van Gemert, Jan (2025): Data underlying the publication/thesis chapter: Learning to Adapt to Position Bias in Vision Transformer Classifiers. Version 1. 4TU.ResearchData. software. https://doi.org/10.4121/471ed486-bc86-40de-9e1d-9446cd6ec5aa.v1

Categories

• Artificial Intelligence and Image Processing
• Information and Computing Sciences

Keywords

computer vision position bias position embeddings Vision Transformers

Licence

CC BY 4.0

Interoperability

• RO-Crate Metadata

Export as...

RefWorks BibTeX Reference Manager Endnote DataCite NLM DC CFF

by Robert-Jan Bruintjes , Jan van Gemert

This article proposes a novel method to measure learned position bias in Vision Transformers, and investigates which model design choices affect learned equivariance.

History

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

Publisher

4TU.ResearchData

Format

GitHub repository containing Python code.

Associated peer-reviewed publication

Learning to Adapt to Position Bias in Vision Transformer Classifiers

References

• https://arxiv.org/abs/2505.13137

Organizations

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