Skip to content

Read-only version: For security reasons, the Research Information System (FIS) has been temporarily replaced by this read-only version. All public content and full texts remain available; login, editing, submission and statistics are not available. Questions: fis@uni-bamberg.de

Home › Publications › Self-supervised Vision Transformer are Scalable Generative Models for Domain Generalization

Publication

Self-supervised Vision Transformer are Scalable Generative Models for Domain Generalization

Doerrich, Sebastian; Di Salvo, Francesco; Ledig, Christian (2024): Self-supervised Vision Transformer are Scalable Generative Models for Domain Generalization, in: Marius George Linguraru, Qi Dou, Aasa Feragen, u. a. (Hrsg.), Medical Image Computing and Computer Assisted Intervention – MICCAI 2024, Cham: Springer Nature Switzerland, S. 644–654, doi: 10.1007/978-3-031-72117-5_60.

Details

Faculty/Chair
Faculty/Professorship
Author
By
Doerrich, Sebastian; ...
Title of the compilation
Medical Image Computing and Computer Assisted Intervention – MICCAI 2024
Editors
Linguraru, Marius George
Dou, Qi
Feragen, Aasa
Giannarou, Stamatia
Glocker, Ben
Lekadir, Karim
Schnabel, Julia A.
Conference
27th International Conference on Medical Image Computing and Computer Assisted Intervention (MICCAI), October 6–10, 2024, Marrakesh, Morocco
Publisher Information
Springer Nature Switzerland : Cham
Year of publication
2024
ISBN
978-3-031-72117-5
Language
English
DOI
Abstract

Despite notable advancements, the integration of deep learning (DL) techniques into impactful clinical applications, particularly in the realm of digital histopathology, has been hindered by challenges associated with achieving robust generalization across diverse imaging domains and characteristics. Traditional mitigation strategies in this field such as data augmentation and stain color normalization have proven insufficient in addressing this limitation, necessitating the exploration of alternative methodologies. To this end, we propose a novel generative method for domain generalization in histopathology images. Our method employs a generative, self-supervised Vision Transformer to dynamically extract characteristics of image patches and seamlessly infuse them into the original images, thereby creating novel, synthetic images with diverse attributes. By enriching the dataset with such synthesized images, we aim to enhance its holistic nature, facilitating improved generalization of DL models to unseen domains. Extensive experiments conducted on two distinct histopathology datasets demonstrate the effectiveness of our proposed approach, outperforming the state of the art substantially, on the Camelyon17-wilds challenge dataset (+2%) and on a second epithelium-stroma dataset (+26%). Furthermore, we emphasize our method's ability to readily scale with increasingly available unlabeled data samples and more complex, higher parametric architectures. Source code is available at https://github.com/sdoerrich97/vits-are-generative-models.

GND Keywords
Generalisierung
Anwendungsbereich
Maschinelles Lernen
Feature-Technologie
Orthogonalisierung
Image
Keywords
domain generalization
self-supervised learning
feature orthogonalization
generative image synthesis
DDC Classification
004 Computer science
RVK Classification
ST 304
Peer Reviewed
yes
International Distribution
yes
Type
Conferenceobject
URI
Activation date
2024-12-06

Permalink: https://fis.uni-bamberg.de/handle/uniba/105289 · Data as JSON · Cite: BibTeX · RIS

Data as of: 2026-11-16

Restricted read-only access: login, editing and submission are temporarily disabled.