mlsanityData to 7 Oct 2026

Learning Disentangled Representations in the Imaging Domain

arXiv 2108.12043 ↗First posted 26 Aug 2021cs.CV cs.LGcited by 46

Not on the map. Why?

Abstract (arXiv)

Disentangled representation learning has been proposed as an approach to learning general representations even in the absence of, or with limited, supervision. A good general representation can be fine-tuned for new target tasks using modest amounts of data, or used directly in unseen domains achieving remarkable performance in the corresponding task. This alleviation of the data and annotation requirements offers tantalising prospects for applications in computer vision and healthcare. In this tutorial paper, we motivate the need for disentangled representations, revisit key concepts, and describe practical building blocks and criteria for learning such representations. We survey applications in medical imaging emphasising choices made in exemplar key works, and then discuss links to computer vision applications. We conclude by presenting limitations, challenges, and opportunities.

Key facts. Cited by 46 papers in the map (data through 7 Oct 2026). Builds on 183 of its 286 references that are in the map. First posted on arXiv 26 Aug 2021.

Builds on

183 of 286 references.

References · 183

  1. 2017Attention Is All You Needcited by 59,932
  2. 2015U-Net: Convolutional Networks for Biomedical Image Segmentationcited by 19,604
  3. 2020A Simple Framework for Contrastive Learning of Visual Representationscited by 11,979
  4. 2019Momentum Contrast for Unsupervised Visual Representation Learningcited by 7,482
  5. 2015Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shiftcited by 6,979
  6. 2018A Style-Based Generator Architecture for Generative Adversarial Networkscited by 5,986
  7. 2016Feature Pyramid Networks for Object Detectioncited by 5,021
  8. 2020Bootstrap your own latent: A new approach to self-supervised Learningcited by 4,712
  9. 2017Neural Discrete Representation Learningcited by 4,650
  10. 2016The Cityscapes Dataset for Semantic Urban Scene Understandingcited by 4,427
  11. 2019Analyzing and Improving the Image Quality of StyleGANcited by 3,580
  12. 2015ShapeNet: An Information-Rich 3D Model Repositorycited by 2,880
38 more
  1. 2016Categorical Reparameterization with Gumbel-Softmaxcited by 2,708
  2. 2016Perceptual Losses for Real-Time Style Transfer and Super-Resolutioncited by 2,678
  3. 2018Large Scale GAN Training for High Fidelity Natural Image Synthesiscited by 2,609
  4. 2017FiLM: Visual Reasoning with a General Conditioning Layercited by 2,286
  5. 2017Improved Training of Wasserstein GANscited by 2,223
  6. 2015Variational Inference with Normalizing Flowscited by 2,161
  7. 2017Arbitrary Style Transfer in Real-time with Adaptive Instance Normalizationcited by 1,998
  8. 2014Unsupervised Domain Adaptation by Backpropagationcited by 1,906
  9. 2019Invariant Risk Minimizationcited by 1,832
  10. 2021Barlow Twins: Self-Supervised Learning via Redundancy Reductioncited by 1,818
  11. 2018Glow: Generative Flow with Invertible 1x1 Convolutionscited by 1,539
  12. 2019MixMatch: A Holistic Approach to Semi-Supervised Learningcited by 1,390
  13. 2020Big Self-Supervised Models are Strong Semi-Supervised Learnerscited by 1,375
  14. 2019Normalizing Flows for Probabilistic Modeling and Inferencecited by 1,315
  15. 2019Semantic Image Synthesis with Spatially-Adaptive Normalizationcited by 1,295
  16. 2016Group Equivariant Convolutional Networkscited by 1,154
  17. 2021Geometric Deep Learning: Grids, Groups, Graphs, Geodesics, and Gaugescited by 1,131
  18. 2017CyCADA: Cycle-Consistent Adversarial Domain Adaptationcited by 1,079
  19. 2014NICE: Non-linear Independent Components Estimationcited by 1,052
  20. 2016Least Squares Generative Adversarial Networkscited by 1,000
  21. 2018Challenging Common Assumptions in the Unsupervised Learning of Disentangled Representationscited by 929
  22. 2020Object-Centric Learning with Slot Attentioncited by 865
  23. 2016InfoGAN: Interpretable Representation Learning by Information Maximizing Generative Adversarial Netscited by 858
  24. 2018Multimodal Unsupervised Image-to-Image Translationcited by 795
  25. 2017Learning to Generalize: Meta-Learning for Domain Generalizationcited by 762
  26. 2021Generalizing to Unseen Domains: A Survey on Domain Generalizationcited by 762
  27. 2020Out-of-Distribution Generalization via Risk Extrapolation (REx)cited by 737
  28. 2018MINE: Mutual Information Neural Estimationcited by 680
  29. 2013Speech Recognition with Deep Recurrent Neural Networkscited by 666
  30. 2020Contrastive Learning for Unpaired Image-to-Image Translationcited by 637
  31. 2020The Future of Digital Health with Federated Learningcited by 625
  32. 2018Disentangling by Factorisingcited by 614
  33. 2019Neural Spline Flowscited by 590
  34. 2019Variational Autoencoders and Nonlinear ICA: A Unifying Frameworkcited by 494
  35. 2019PointFlow: 3D Point Cloud Generation with Continuous Normalizing Flowscited by 487
  36. 2020Closed-Form Factorization of Latent Semantics in GANscited by 407
  37. 2018Pyro: Deep Universal Probabilistic Programmingcited by 379
  38. 2016Adversarial Feature Learningcited by 350

50 most cited of 183 All 183 (JSON)

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2022: 10; 2023: 9; 2024: 14; 2025: 10; 2026: 3.

46 papers.

Sort:

By area:

  1. 2023Multi-modal Learning with Missing Modality via Shared-Specific Feature Modellingcited by 159
  2. 2022Disentangled Representation Learningcited by 111
  3. 2022Causal Machine Learning for Healthcare and Precision Medicinecited by 68
  4. 2024Causal Diffusion Autoencoders: Toward Counterfactual Generation via Diffusion Probabilistic Modelscited by 17
  5. 2022Controlled Generation of Unseen Faults for Partial and Open-Partial Domain Adaptationcited by 10
  6. 2023SE(3)-Equivariant and Noise-Invariant 3D Rigid Motion Tracking in Brain MRIcited by 10
  7. 2024Enhancing Feature Diversity Boosts Channel-Adaptive Vision Transformerscited by 10
  8. 2022Domain Adaptation for Underwater Image Enhancement via Content and Style Separationcited by 9
  9. 2022Review of Disentanglement Approaches for Medical Applications -- Towards Solving the Gordian Knot of Generative Models in Healthcarecited by 9
  10. 2024Disentangling representations of retinal images with generative modelscited by 8
  11. 2022Representation Learning with Diffusion Modelscited by 6
  12. 2023Sketch-based Medical Image Retrievalcited by 6
34 more
  1. 2023Learning Disentangled Semantic Spaces of Explanations via Invertible Neural Networkscited by 6
  2. 2022A Comprehensive Review of Trends, Applications and Challenges In Out-of-Distribution Detectioncited by 5
  3. 2024A survey of recent methods for addressing AI fairness and bias in biomedicinecited by 5
  4. 2024Sequential Representation Learning via Static-Dynamic Conditional Disentanglementcited by 4
  5. 2023A Causal Ordering Prior for Unsupervised Representation Learningcited by 3
  6. 2024Pooling Image Datasets With Multiple Covariate Shift and Imbalancecited by 3
  7. 2025Decoupling Clinical and Class-Agnostic Features for Reliable Few-Shot Adaptation under Shiftcited by 3
  8. 2023Compositionally Equivariant Representation Learningcited by 2
  9. 2024Deformation-aware GAN for Medical Image Synthesis with Substantially Misaligned Pairscited by 2
  10. 2025Causal Disentanglement for Robust Long-tail Medical Image Generationcited by 2
  11. 2025In-hoc Concept Representations to Regularise Deep Learning in Medical Imagingcited by 2
  12. 2026Mitigating Translationese Bias in Multilingual LLM-as-a-Judge via Disentangled Information Bottleneckcited by 2
  13. 2022HSIC-InfoGAN: Learning Unsupervised Disentangled Representations by Maximising Approximated Mutual Informationcited by 1
  14. 2023Reliable Federated Disentangling Network for Non-IID Domain Featurecited by 1
  15. 2023Towards Domain-Specific Features Disentanglement for Domain Generalizationcited by 1
  16. 2024Causal Prototype-inspired Contrast Adaptation for Unsupervised Domain Adaptive Semantic Segmentation of High-resolution Remote Sensing Imagerycited by 1
  17. 2024Boosting Few-Shot Learning with Disentangled Self-Supervised Learning and Meta-Learning for Medical Image Classificationcited by 1
  18. 2024FedGS: Federated Gradient Scaling for Heterogeneous Medical Image Segmentationcited by 1
  19. 2024Human-AI Collaborative Multi-modal Multi-rater Learning for Endometriosis Diagnosiscited by 1
  20. 2025OWT: A Foundational Organ-Wise Tokenization Framework for Medical Imagingcited by 1
  21. 2025Causal Representation Learning with Observational Grouping for CXR Classificationcited by 1
  22. 2025DiViD: Disentangled Video Diffusion for Static-Dynamic Factorizationcited by 1
  23. 2022Towards Disentangling Information Paths with Coded ResNeXtcited by 0
  24. 2022Learning Generative Factors of EEG Data with Variational auto-encoderscited by 0
  25. 2023Interpretability-guided Data Augmentation for Robust Segmentation in Multi-centre Colonoscopy Datacited by 0
  26. 2024DualContrast: Unsupervised Disentangling of Content and Transformations with Implicit Parameterizationcited by 0
  27. 2024The Interpretability of Codebooks in Model-Based Reinforcement Learning is Limitedcited by 0
  28. 2024Enhancing Cross-Modal Medical Image Segmentation through Compositionalitycited by 0
  29. 2025ConceptVAE: Self-Supervised Fine-Grained Concept Disentanglement from 2D Echocardiographiescited by 0
  30. 2025A Multi-Centric Anthropomorphic 3D CT Phantom-Based Benchmark Dataset for Harmonizationcited by 0
  31. 2025Beyond Correlation: Learning Supervised, Sample-Distinct, and Eigenimage-Interpretable Representationscited by 0
  32. 2025Multimodal Medical Endoscopic Image Analysis via Progressive Disentangle-aware Contrastive Learningcited by 0
  33. 2026Cross-Camera Cow Identification via Disentangled Representation Learningcited by 0
  34. 2026MeDUET: Disentangled Unified Pretraining for 3D Medical Image Synthesis and Analysiscited by 0