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 › Unsupervised Feature Orthogonalization for Learning Distortion-Invariant Representations

Publication

Unsupervised Feature Orthogonalization for Learning Distortion-Invariant Representations

Doerrich, Sebastian; Di Salvo, Francesco; Ledig, Christian (2025): Unsupervised Feature Orthogonalization for Learning Distortion-Invariant Representations, in: Bamberg: Otto-Friedrich-Universität, S. 1–13.

Details

Faculty/Chair
Faculty/Professorship
Author
By
Doerrich, Sebastian; ...
Publisher Information
Otto-Friedrich-Universität : Bamberg
Year of publication
2025
Source/Other editions
Workshop Proceedings : International Workshop on Robust Recognition in the Open World at The 35th British Machine Vision Conference, 2024, S. 1–13
Year of first publication
2024
Language
English
Licence
URN
Abstract

This study introduces unORANIC+, a novel method that integrates unsupervised feature orthogonalization with the ability of a Vision Transformer to capture both local and global relationships for improved robustness and generalizability. The streamlined architecture of unORANIC+ effectively separates anatomical and image-specific attributes, resulting in robust and unbiased latent representations that allow the model to demonstrate excellent performance across various medical image analysis tasks and diverse datasets. Extensive experimentation demonstrates unORANIC+’s reconstruction proficiency, corruption resilience, as well as capability to revise existing image distortions. Additionally, the model exhibits notable aptitude in downstream tasks such as disease classification and corruption detection. We confirm its adaptability to diverse datasets of varying image sources and sample sizes which positions the method as a promising algorithm for advanced medical image analysis, particularly in resourceconstrained environments lacking large, tailored datasets. The source code is available at github.com/sdoerrich97/unoranic-plus.

GND Keywords
Unüberwachtes Lernen
Generalisierung
Bildanalyse
Medizin
Keywords
feature orthogonalization
robustness
corruption revision
unsupervised learning
generalization
DDC Classification
004 Computer science
RVK Classification
ST 300
Peer Reviewed
yes
International Distribution
yes
Type
Conferenceobject
URI
Activation date
2025-10-27

Permalink: https://fis.uni-bamberg.de/handle/uniba/109529 · Data as JSON · Cite: BibTeX · RIS

Data as of: 2026-11-16

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