mlsanityData to 7 Oct 2026

SepVAE: a contrastive VAE to separate pathological patterns from healthy ones

arXiv 2307.06206 ↗First posted 12 Jul 2023cs.CV stat.MLcited by 10

Not on the map. Why?

Abstract (arXiv)

Contrastive Analysis VAE (CA-VAEs) is a family of Variational auto-encoders (VAEs) that aims at separating the common factors of variation between a background dataset (BG) (i.e., healthy subjects) and a target dataset (TG) (i.e., patients) from the ones that only exist in the target dataset. To do so, these methods separate the latent space into a set of salient features (i.e., proper to the target dataset) and a set of common features (i.e., exist in both datasets). Currently, all models fail to prevent the sharing of information between latent spaces effectively and to capture all salient factors of variation. To this end, we introduce two crucial regularization losses: a disentangling term between common and salient representations and a classification term between background and target samples in the salient space. We show a better performance than previous CA-VAEs methods on three medical applications and a natural images dataset (CelebA). Code and datasets are available on GitHub https://github.com/neurospin-projects/2023_rlouiset_sepvae.

Key facts. Cited by 10 papers in the map (data through 7 Oct 2026). Builds on 16 of its 41 references that are in the map. First posted on arXiv 12 Jul 2023.

Builds on

16 of 41 references.

References · 16

  1. 2014Deep Learning Face Attributes in the Wildcited by 3,679
  2. 2018Disentangling by Factorisingcited by 614
  3. 2014Semi-Supervised Learning with Deep Generative Modelscited by 494
  4. 2019Variational Autoencoders and Nonlinear ICA: A Unifying Frameworkcited by 494
  5. 2018Understanding disentangling in β-VAEcited by 332
  6. 2021Self-Supervised Learning with Data Augmentations Provably Isolates Content from Stylecited by 308
  7. 2016Auxiliary Deep Generative Modelscited by 72
  8. 2020Capturing Label Characteristics in VAEscited by 30
  9. 2019Contrastive Variational Autoencoder Enhances Salient Featurescited by 28
  10. 2018Disentangling Latent Space for VAE by Label Relevant/Irrelevant Dimensionscited by 19
  11. 2017Disentangled Variational Auto-Encoder for Semi-supervised Learningcited by 17
  12. 2018Unsupervised learning with contrastive latent variable modelscited by 15
4 more
  1. 2022Moment Matching Deep Contrastive Latent Variable Modelscited by 13
  2. 2021Contrastive latent variable modeling with application to case-control sequencing experimentscited by 9
  3. 2015Rich Component Analysiscited by 6
  4. 2019Learning Disentangled Representations with Reference-Based Variational Autoencoderscited by 6

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 3; 2025: 2; 2026: 5.

10 papers.

  1. 2024Separating common from salient patterns with Contrastive Representation Learningcited by 6
  2. 2024Toward the Identifiability of Comparative Deep Generative Modelscited by 4
  3. 2025Learning Common and Salient Generative Factors Between Two Image Datasetscited by 3
  4. 2026Automatic Discovery of Disease Subgroups by Contrasting with Healthy Controlscited by 2
  5. 2024Unsupervised contrastive analysis for anomaly detection in brain MRIs via conditional diffusion modelscited by 1
  6. 2025CLEAR: Unlearning Spurious Style-Content Associations with Contrastive LEarning with Anti-contrastive Regularizationcited by 1
  7. 2026Diff-CA: Separating Common and Salient Factors with Diffusion Modelscited by 1
  8. 2026CASL-VAE: Learning Structured Latent Variables from Unpaired Data for Semi-supervised Clustering and Paired Sample Generationcited by 0
  9. 2026Counterfactual Contrastive Analysiscited by 0
  10. 2026SAGE: Salient Factor Discovery and Generation with Visual Foundation Representationscited by 0