mlsanityData to 14 Oct 2026

unORANIC: Unsupervised Orthogonalization of Anatomy and Image-Characteristic Features

arXiv 2308.15507 ↗First posted 29 Aug 2023eess.IV cs.CV cs.LGcited by 3

Not on the map. Why?

Abstract (arXiv)

We introduce unORANIC, an unsupervised approach that uses an adapted loss function to drive the orthogonalization of anatomy and image-characteristic features. The method is versatile for diverse modalities and tasks, as it does not require domain knowledge, paired data samples, or labels. During test time unORANIC is applied to potentially corrupted images, orthogonalizing their anatomy and characteristic components, to subsequently reconstruct corruption-free images, showing their domain-invariant anatomy only. This feature orthogonalization further improves generalization and robustness against corruptions. We confirm this qualitatively and quantitatively on 5 distinct datasets by assessing unORANIC's classification accuracy, corruption detection and revision capabilities. Our approach shows promise for enhancing the generalizability and robustness of practical applications in medical image analysis. The source code is available at https://github.com/sdoerrich97/unORANIC.

Key facts. Cited by 3 papers in the map (data through 14 Oct 2026). Builds on 16 of its 29 references that are in the map. First posted on arXiv 29 Aug 2023.

Builds on

16 of 29 references.

References · 16

  1. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  2. 2015U-Net: Convolutional Networks for Biomedical Image Segmentationcited by 19,713
  3. 2019Benchmarking Neural Network Robustness to Common Corruptions and Perturbationscited by 2,877
  4. 2021MedMNIST v2 -- A large-scale lightweight benchmark for 2D and 3D biomedical image classificationcited by 690
  5. 2019Skin Lesion Analysis Toward Melanoma Detection 2018: A Challenge Hosted by the International Skin Imaging Collaboration (ISIC)cited by 669
  6. 2018Albumentations: fast and flexible image augmentationscited by 560
  7. 2019Benchmarking Robustness in Object Detection: Autonomous Driving when Winter is Comingcited by 336
  8. 2023WinCLIP: Zero-/Few-Shot Anomaly Classification and Segmentationcited by 315
  9. 2020MedMNIST Classification Decathlon: A Lightweight AutoML Benchmark for Medical Image Analysiscited by 206
  10. 2023MedViT: A Robust Vision Transformer for Generalized Medical Image Classificationcited by 89
  11. 2019Disentangled Representation Learning in Cardiac Image Analysiscited by 69
  12. 2020Learning Invariant Representations and Risks for Semi-supervised Domain Adaptationcited by 69
4 more
  1. 2019Fence GAN: Towards Better Anomaly Detectioncited by 32
  2. 2019Deep Learning Based Detection and Correction of Cardiac MR Motion Artefacts During Reconstruction for High-Quality Segmentationcited by 18
  3. 2018HybridNet: Classification and Reconstruction Cooperation for Semi-Supervised Learningcited by 8
  4. 2023Boosting multiple sclerosis lesion segmentation through attention mechanismcited by 8

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2024: 1; 2025: 1; 2026: 1.

3 papers.

  1. 2025Manifold Topological Deep Learning for Biomedical Datacited by 4
  2. 2024Unsupervised Feature Orthogonalization for Learning Distortion-Invariant Representationscited by 0
  3. 2026Combinatorial Network-Based Manifold Topological Deep Learning for Image Analysiscited by 0