mlsanityData to 14 Oct 2026

Causal Representation Learning with Observational Grouping for CXR Classification

arXiv 2506.20582 ↗First posted 25 Jun 2025cs.CV cs.AI cs.LGcited by 1

Not on the map. Why?

Abstract (arXiv)

Identifiable causal representation learning seeks to uncover the true causal relationships underlying a data generation process. In medical imaging, this presents opportunities to improve the generalisability and robustness of task-specific latent features. This work introduces the concept of grouping observations to learn identifiable representations for disease classification in chest X-rays via an end-to-end framework. Our experiments demonstrate that these causal representations improve generalisability and robustness across multiple classification tasks when grouping is used to enforce invariance w.r.t race, sex, and imaging views.

Key facts. Cited by 1 paper in the map (data through 14 Oct 2026). Builds on 25 of its 36 references that are in the map. First posted on arXiv 25 Jun 2025.

Builds on

25 of 36 references.

References · 25

  1. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  2. 2016Densely Connected Convolutional Networkscited by 6,720
  3. 2019EfficientNet: Rethinking Model Scaling for Convolutional Neural Networkscited by 6,442
  4. 2019CheXpert: A Large Chest Radiograph Dataset with Uncertainty Labels and Expert Comparisoncited by 1,423
  5. 2018Challenging Common Assumptions in the Unsupervised Learning of Disentangled Representationscited by 941
  6. 2019MIMIC-CXR-JPG, a large publicly available database of labeled chest radiographscited by 597
  7. 2019Variational Autoencoders and Nonlinear ICA: A Unifying Frameworkcited by 503
  8. 2017CheXNet: Radiologist-Level Pneumonia Detection on Chest X-Rays with Deep Learningcited by 461
  9. 2021Self-Supervised Learning with Data Augmentations Provably Isolates Content from Stylecited by 312
  10. 2020Weakly-Supervised Disentanglement Without Compromisescited by 239
  11. 2021Contrastive Learning Inverts the Data Generating Processcited by 221
  12. 2019Causality matters in medical imagingcited by 193
13 more
  1. 2021Reading Race: AI Recognises Patient's Racial Identity In Medical Imagescited by 156
  2. 2020Contrastive learning, multi-view redundancy, and linear modelscited by 146
  3. 2022Interventional Causal Representation Learningcited by 142
  4. 2022Weakly supervised causal representation learningcited by 140
  5. 2020ICE-BeeM: Identifiable Conditional Energy-Based Deep Models Based on Nonlinear ICAcited by 102
  6. 2023Multi-View Causal Representation Learning with Partial Observabilitycited by 74
  7. 2023Score-based Causal Representation Learning with Interventionscited by 49
  8. 2021Learning Disentangled Representations in the Imaging Domaincited by 46
  9. 2020Fundamental Limits and Tradeoffs in Invariant Representation Learningcited by 38
  10. 2023Causal Representation Learning Made Identifiable by Grouping of Observational Variablescited by 32
  11. 2024Unifying Causal Representation Learning with the Invariance Principlecited by 31
  12. 2024Counterfactual contrastive learning: robust representations via causal image synthesiscited by 11
  13. 2023Are demographically invariant models and representations in medical imaging fair?cited by 6

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2026: 1.

1 paper.

  1. 2026Causal Transfer in Medical Image Analysiscited by 0