Zum Inhalt springen

Nur-Lesen-Fassung: Das Forschungsinformationssystem (FIS) ist aus Sicherheitsgründen vorübergehend durch diese Nur-Lesen-Fassung ersetzt. Alle öffentlichen Inhalte und Volltexte sind weiterhin abrufbar; Anmeldung, Bearbeitung, Einreichung und Statistiken stehen nicht zur Verfügung. Bei Fragen: fis@uni-bamberg.de

Start › Publikationen › Stylizing ViT : Anatomy-Preserving Instance Style Transfer for Domain Generalization

Publikation

Stylizing ViT : Anatomy-Preserving Instance Style Transfer for Domain Generalization

Doerrich, Sebastian; Di Salvo, Francesco; Alle, Jonas; u. a. (2026): Stylizing ViT : Anatomy-Preserving Instance Style Transfer for Domain Generalization, in: 2026 IEEE 23rd International Symposium on Biomedical Imaging (ISBI), Piscataway, NJ: IEEE, doi: 10.1109/isbi61048.2026.11515498.

Details

Fakultät/Lehrstuhl
Autorin(nen)/Autor(en)
Titel des Sammelwerks
2026 IEEE 23rd International Symposium on Biomedical Imaging (ISBI)
Konferenz
23rd International Symposium on Biomedical Imaging (ISBI), 08-11 April 2026, London
Verlagsangabe
IEEE : Piscataway, NJ
Erscheinungsjahr
2026
Seiten
5
Sprache(n)
Englisch
DOI
URL
Abstract

Deep learning models in medical image analysis often struggle with generalizability across domains and demographic groups due to data heterogeneity and scarcity. Traditional augmentation improves robustness, but fails under substantial domain shifts. Recent advances in stylistic augmentation enhance domain generalization by varying image styles but fall short in terms of style diversity or by introducing artifacts into the generated images. To address these limitations, we propose Stylizing ViT, a novel Vision Transformer encoder that utilizes weight-shared attention blocks for both self- and cross-attention. This design allows the same attention block to maintain anatomical consistency through self-attention while performing style transfer via cross-attention. We assess the effectiveness of our method for domain generalization by employing it for data augmentation on three distinct image classification tasks in the context of histopathology and dermatology. Results demonstrate an improved robustness (up to +13% accuracy) over the state of the art while generating perceptually convincing images without artifacts. Additionally, we show that Stylizing ViT is effective beyond training, achieving a 17% performance improvement during inference when used for test-time augmentation. The source code is available at https://github.com/sdoerrich97/stylizing-vit .

Freie Schlagwort(e)
style transfer
domain generalization
crossattention
data augmentation
vision transformer
Peer Reviewed
ja
Internationale Verbreitung
ja
Dokumenttyp
Konferenzveröffentlichung
URI
Datum der Freischaltung
09.09.2026

Permalink: https://fis.uni-bamberg.de/handle/uniba/117126 · Daten als JSON · Zitieren: BibTeX · RIS

Datenstand: 16.11.2026

Eingeschränkter Lesezugriff: Anmeldung, Bearbeitung und Einreichung sind vorübergehend deaktiviert.