Unsupervised Feature Orthogonalization for Learning Distortion-Invariant Representations

TL;DR

unORANIC+ is an unsupervised method that orthogonalizes features in vision transformers to learn robust, distortion-invariant representations for medical image analysis, demonstrating superior performance across tasks and datasets.

Contribution

The paper introduces unORANIC+, a novel unsupervised feature orthogonalization technique integrated with vision transformers, enhancing robustness and generalizability in medical imaging.

Findings

Effective separation of anatomical and image-specific attributes.

High reconstruction quality and corruption resilience.

Improved performance in disease classification and distortion correction.

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 resource-constrained environments lacking large, tailored datasets. The source code is available at https://github.com/sdoerrich97/unoranic-plus .