# Learning Disentangled Representations with Reference-Based Variational Autoencoders

arXiv: https://arxiv.org/abs/1901.08534 · HTML: https://mlsanity.com/paper/1901.08534/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 24 Jan 2019.

## Built on by (most cited first, 6 of 6)

- [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)
- [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)
- [Disentangled representations: towards interpretation of sex determination from hip bone](https://mlsanity.com/paper/2112.09414/) (2021)

## Abstract (arXiv)

Learning disentangled representations from visual data, where different high-level generative factors are independently encoded, is of importance for many computer vision tasks. Solving this problem, however, typically requires to explicitly label all the factors of interest in training images. To alleviate the annotation cost, we introduce a learning setting which we refer to as "reference-based disentangling". Given a pool of unlabeled images, the goal is to learn a representation where a set of target factors are disentangled from others. The only supervision comes from an auxiliary "reference set" containing images where the factors of interest are constant. In order to address this problem, we propose reference-based variational autoencoders, a novel deep generative model designed to exploit the weak-supervision provided by the reference set. By addressing tasks such as feature learning, conditional image generation or attribute transfer, we validate the ability of the proposed model to learn disentangled representations from this minimal form of supervision.