Saved in:
Bibliographic Details
Main Authors: Pawlowsky, Moritz, Vamvakeros, Antonis, Weiss, Alexander, Bielefeld, Anja, Cooper, Samuel J., Docherty, Ronan
Format: Preprint
Published: 2026
Subjects:
Online Access:https://arxiv.org/abs/2603.16840
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866914402749382656
author Pawlowsky, Moritz
Vamvakeros, Antonis
Weiss, Alexander
Bielefeld, Anja
Cooper, Samuel J.
Docherty, Ronan
author_facet Pawlowsky, Moritz
Vamvakeros, Antonis
Weiss, Alexander
Bielefeld, Anja
Cooper, Samuel J.
Docherty, Ronan
contents Vision transformers (ViTs) - especially feature foundation models like DINOv2 - learn rich representations useful for many downstream tasks. However, architectural choices (such as positional encoding) can lead to these models displaying positional biases and artefacts independent of semantic content. This makes zero-shot adaption difficult in fields like material science, where images are often cross-sections of homogeneous microstructure (i.e. having no preferred direction). In this work, we investigate the positional bias in ViTs via linear probing, finding it present across a range of objectives and positional encodings, and subsequently reduce it by finetuning models to use ALiBi relative positional encoding. We demonstrate that these models retain desirable general semantics and their unbiased features can be used successfully in trainable segmentation of complex microscopy images.
format Preprint
id arxiv_https___arxiv_org_abs_2603_16840
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle What DINO saw: ALiBi positional encoding reduces positional bias in Vision Transformers
Pawlowsky, Moritz
Vamvakeros, Antonis
Weiss, Alexander
Bielefeld, Anja
Cooper, Samuel J.
Docherty, Ronan
Computer Vision and Pattern Recognition
Materials Science
Vision transformers (ViTs) - especially feature foundation models like DINOv2 - learn rich representations useful for many downstream tasks. However, architectural choices (such as positional encoding) can lead to these models displaying positional biases and artefacts independent of semantic content. This makes zero-shot adaption difficult in fields like material science, where images are often cross-sections of homogeneous microstructure (i.e. having no preferred direction). In this work, we investigate the positional bias in ViTs via linear probing, finding it present across a range of objectives and positional encodings, and subsequently reduce it by finetuning models to use ALiBi relative positional encoding. We demonstrate that these models retain desirable general semantics and their unbiased features can be used successfully in trainable segmentation of complex microscopy images.
title What DINO saw: ALiBi positional encoding reduces positional bias in Vision Transformers
topic Computer Vision and Pattern Recognition
Materials Science
url https://arxiv.org/abs/2603.16840