# Contrastive Variational Autoencoder Enhances Salient Features

arXiv: https://arxiv.org/abs/1902.04601 · HTML: https://mlsanity.com/paper/1902.04601/

## Key facts

- Cited by 28 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 12 Feb 2019.

## Built on by (most cited first, 28 of 28)

- [Uncertainty Inspired Underwater Image Enhancement](https://mlsanity.com/paper/2207.09689/) (2022)
- [SwitchTab: Switched Autoencoders Are Effective Tabular Learners](https://mlsanity.com/paper/2401.02013/) (2024)
- [Moment Matching Deep Contrastive Latent Variable Models](https://mlsanity.com/paper/2202.10560/) (2022)
- [SepVAE: a contrastive VAE to separate pathological patterns from healthy ones](https://mlsanity.com/paper/2307.06206/) (2023)
- [Double InfoGAN for Contrastive Analysis](https://mlsanity.com/paper/2401.17776/) (2024)
- [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)
- [Feature Selection in the Contrastive Analysis Setting](https://mlsanity.com/paper/2310.18531/) (2023)
- [C2VAE: Gaussian Copula-based VAE Differing Disentangled from Coupled Representations with Contrastive Posterior](https://mlsanity.com/paper/2309.13303/) (2023)
- [Contrastive independent component analysis](https://mlsanity.com/paper/2407.02357/) (2024)
- [A Data-Driven Prism: Multi-View Source Separation with Diffusion Model Priors](https://mlsanity.com/paper/2510.05205/) (2025)
- [H-SPLID: HSIC-based Saliency Preserving Latent Information Decomposition](https://mlsanity.com/paper/2510.20627/) (2025)
- [Capturing patterns of variation unique to a specific dataset](https://mlsanity.com/paper/2104.08157/) (2021)
- [Multimodal Understanding Through Correlation Maximization and Minimization](https://mlsanity.com/paper/2305.03125/) (2023)
- [Disentangling Interpretable Factors with Supervised Independent Subspace Principal Component Analysis](https://mlsanity.com/paper/2410.23595/) (2024)
- [CLEAR: Unlearning Spurious Style-Content Associations with Contrastive LEarning with Anti-contrastive Regularization](https://mlsanity.com/paper/2507.18794/) (2025)
- [Contrastive Dimension Reduction: A Systematic Review](https://mlsanity.com/paper/2510.11847/) (2025)
- [Diff-CA: Separating Common and Salient Factors with Diffusion Models](https://mlsanity.com/paper/2606.06120/) (2026)
- [Green for Go, Red for No: Visual Grounding via Semantic Segmentation for VLA Navigation Policies](https://mlsanity.com/paper/2607.05122/) (2026)
- [Autism Spectrum Disorder Classification with Interpretability in Children based on Structural MRI Features Extracted using Contrastive Variational Autoencoder](https://mlsanity.com/paper/2307.00976/) (2023)
- [Clustering-friendly Representation Learning for Enhancing Salient Features](https://mlsanity.com/paper/2408.04891/) (2024)
- [Modeling variable guide efficiency in pooled CRISPR screens with ContrastiveVI+](https://mlsanity.com/paper/2411.08072/) (2024)
- [Disentanglement of Biological and Technical Factors via Latent Space Rotation in Clinical Imaging Improves Disease Pattern Discovery](https://mlsanity.com/paper/2509.11436/) (2025)
- [Frictional Q-Learning](https://mlsanity.com/paper/2509.19771/) (2025)
- [Disentangling Shared and Target-Enriched Topics via Background-Contrastive Non-negative Matrix Factorization](https://mlsanity.com/paper/2602.22387/) (2026)
- [Learning symplectic model reduction based on an approximation theorem of symplectic embeddings](https://mlsanity.com/paper/2606.04623/) (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)
- [SAGE: Salient Factor Discovery and Generation with Visual Foundation Representations](https://mlsanity.com/paper/2609.39635/) (2026)

## Abstract (arXiv)

Variational autoencoders are powerful algorithms for identifying dominant latent structure in a single dataset. In many applications, however, we are interested in modeling latent structure and variation that are enriched in a target dataset compared to some background---e.g. enriched in patients compared to the general population. Contrastive learning is a principled framework to capture such enriched variation between the target and background, but state-of-the-art contrastive methods are limited to linear models. In this paper, we introduce the contrastive variational autoencoder (cVAE), which combines the benefits of contrastive learning with the power of deep generative models. The cVAE is designed to identify and enhance salient latent features. The cVAE is trained on two related but unpaired datasets, one of which has minimal contribution from the salient latent features. The cVAE explicitly models latent features that are shared between the datasets, as well as those that are enriched in one dataset relative to the other, which allows the algorithm to isolate and enhance the salient latent features. The algorithm is straightforward to implement, has a similar run-time to the standard VAE, and is robust to noise and dataset purity. We conduct experiments across diverse types of data, including gene expression and facial images, showing that the cVAE effectively uncovers latent structure that is salient in a particular analysis.