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

arXiv: https://arxiv.org/abs/2307.06206 · HTML: https://mlsanity.com/paper/2307.06206/

## Key facts

- Cited by 10 papers in the map (data through 14 Oct 2026).
- Builds on 16 of its 41 references that are in the map.
- First posted on arXiv 12 Jul 2023.

## Builds on (most cited first, 16 of 16)

- [Deep Learning Face Attributes in the Wild](https://mlsanity.com/paper/1411.7766/) (2014)
- [Disentangling by Factorising](https://mlsanity.com/paper/1802.05983/) (2018)
- [Variational Autoencoders and Nonlinear ICA: A Unifying Framework](https://mlsanity.com/paper/1907.04809/) (2019)
- [Semi-Supervised Learning with Deep Generative Models](https://mlsanity.com/paper/1406.5298/) (2014)
- [Understanding disentangling in β-VAE](https://mlsanity.com/paper/1804.03599/) (2018)
- [Self-Supervised Learning with Data Augmentations Provably Isolates Content from Style](https://mlsanity.com/paper/2106.04619/) (2021)
- [Auxiliary Deep Generative Models](https://mlsanity.com/paper/1602.05473/) (2016)
- [Capturing Label Characteristics in VAEs](https://mlsanity.com/paper/2006.10102/) (2020)
- [Contrastive Variational Autoencoder Enhances Salient Features](https://mlsanity.com/paper/1902.04601/) (2019)
- [Disentangling Latent Space for VAE by Label Relevant/Irrelevant Dimensions](https://mlsanity.com/paper/1812.09502/) (2018)
- [Disentangled Variational Auto-Encoder for Semi-supervised Learning](https://mlsanity.com/paper/1709.05047/) (2017)
- [Unsupervised learning with contrastive latent variable models](https://mlsanity.com/paper/1811.06094/) (2018)
- [Moment Matching Deep Contrastive Latent Variable Models](https://mlsanity.com/paper/2202.10560/) (2022)
- [Contrastive latent variable modeling with application to case-control sequencing experiments](https://mlsanity.com/paper/2102.06731/) (2021)
- [Rich Component Analysis](https://mlsanity.com/paper/1507.03867/) (2015)
- [Learning Disentangled Representations with Reference-Based Variational Autoencoders](https://mlsanity.com/paper/1901.08534/) (2019)

## Built on by (most cited first, 10 of 10)

- [Separating common from salient patterns with Contrastive Representation Learning](https://mlsanity.com/paper/2402.11928/) (2024)
- [Toward the Identifiability of Comparative Deep Generative Models](https://mlsanity.com/paper/2401.15903/) (2024)
- [Learning Common and Salient Generative Factors Between Two Image Datasets](https://mlsanity.com/paper/2512.12800/) (2025)
- [Automatic Discovery of Disease Subgroups by Contrasting with Healthy Controls](https://mlsanity.com/paper/2605.21301/) (2026)
- [Unsupervised contrastive analysis for anomaly detection in brain MRIs via conditional diffusion models](https://mlsanity.com/paper/2406.00772/) (2024)
- [CLEAR: Unlearning Spurious Style-Content Associations with Contrastive LEarning with Anti-contrastive Regularization](https://mlsanity.com/paper/2507.18794/) (2025)
- [Diff-CA: Separating Common and Salient Factors with Diffusion Models](https://mlsanity.com/paper/2606.06120/) (2026)
- [CASL-VAE: Learning Structured Latent Variables from Unpaired Data for Semi-supervised Clustering and Paired Sample Generation](https://mlsanity.com/paper/2607.08254/) (2026)
- [Counterfactual Contrastive Analysis](https://mlsanity.com/paper/2608.19032/) (2026)
- [SAGE: Salient Factor Discovery and Generation with Visual Foundation Representations](https://mlsanity.com/paper/2609.39635/) (2026)

## 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.