mlsanityData to 7 Oct 2026

Tasting the cake: evaluating self-supervised generalization on out-of-distribution multimodal MRI data

arXiv 2103.15914 ↗First posted 29 Mar 2021cs.CVcited by 5

Not on the map. Why?

Abstract (arXiv)

Self-supervised learning has enabled significant improvements on natural image benchmarks. However, there is less work in the medical imaging domain in this area. The optimal models have not yet been determined among the various options. Moreover, little work has evaluated the current applicability limits of novel self-supervised methods. In this paper, we evaluate a range of current contrastive self-supervised methods on out-of-distribution generalization in order to evaluate their applicability to medical imaging. We show that self-supervised models are not as robust as expected based on their results in natural imaging benchmarks and can be outperformed by supervised learning with dropout. We also show that this behavior can be countered with extensive augmentation. Our results highlight the need for out-of-distribution generalization standards and benchmarks to adopt the self-supervised methods in the medical imaging community.

Key facts. Cited by 5 papers in the map (data through 7 Oct 2026). Builds on 20 of its 33 references that are in the map. First posted on arXiv 29 Mar 2021.

Builds on

20 of 33 references.

References · 20

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,160
  3. 2020A Simple Framework for Contrastive Learning of Visual Representationscited by 11,979
  4. 2018Representation Learning with Contrastive Predictive Codingcited by 7,662
  5. 2016Overcoming catastrophic forgetting in neural networkscited by 4,718
  6. 2020Bootstrap your own latent: A new approach to self-supervised Learningcited by 4,712
  7. 2020Exploring Simple Siamese Representation Learningcited by 2,853
  8. 2015Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networkscited by 2,048
  9. 2020Shortcut Learning in Deep Neural Networkscited by 1,928
  10. 2019Contrastive Multiview Codingcited by 1,297
  11. 2018Learning deep representations by mutual information estimation and maximizationcited by 1,265
  12. 2019On the Variance of the Adaptive Learning Rate and Beyondcited by 763
8 more
  1. 2019Learning Representations by Maximizing Mutual Information Across Viewscited by 733
  2. 2014Efficient Object Localization Using Convolutional Networkscited by 226
  3. 2020TorchIO: A Python library for efficient loading, preprocessing, augmentation and patch-based sampling of medical images in deep learningcited by 176
  4. 2016On Deep Multi-View Representation Learning: Objectives and Optimizationcited by 162
  5. 20203D Self-Supervised Methods for Medical Imagingcited by 134
  6. 2020On the surprising similarities between supervised and self-supervised modelscited by 29
  7. 2020Whole MILC: generalizing learned dynamics across tasks, datasets, and populationscited by 11
  8. 2019Prediction of Progression to Alzheimer's disease with Deep InfoMaxcited by 3

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 1; 2022: 0; 2023: 0; 2024: 2; 2025: 1; 2026: 1.

5 papers.

  1. 2024Robust multi-coil MRI reconstruction via self-supervised denoisingcited by 4
  2. 2021Fusing multimodal neuroimaging data with a variational autoencodercited by 2
  3. 2024Evaluating Self-Supervised Learning in Medical Imaging: A Benchmark for Robustness, Generalizability, and Multi-Domain Impactcited by 2
  4. 2025Tumor-anchored deep feature random forests for out-of-distribution detection in lung cancer segmentationcited by 1
  5. 2026Which Pretext Task Transfers? Self-Supervised Pretraining Objectives for Lung Ultrasoundcited by 0