# Style Feature Extraction Using Contrastive Conditioned Variational Autoencoders with Mutual Information Constraints

arXiv: https://arxiv.org/abs/2303.08068 · HTML: https://mlsanity.com/paper/2303.08068/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 28 of its 54 references that are in the map.
- First posted on arXiv 3 Feb 2023.

## Builds on (most cited first, 28 of 28)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [A Simple Framework for Contrastive Learning of Visual Representations](https://mlsanity.com/paper/2002.05709/) (2020)
- [ImageNet Large Scale Visual Recognition Challenge](https://mlsanity.com/paper/1409.0575/) (2014)
- [Momentum Contrast for Unsupervised Visual Representation Learning](https://mlsanity.com/paper/1911.05722/) (2019)
- [Deep Learning Face Attributes in the Wild](https://mlsanity.com/paper/1411.7766/) (2014)
- [Domain-Adversarial Training of Neural Networks](https://mlsanity.com/paper/1505.07818/) (2015)
- [Exploring Simple Siamese Representation Learning](https://mlsanity.com/paper/2011.10566/) (2020)
- [Unsupervised Learning of Visual Features by Contrasting Cluster Assignments](https://mlsanity.com/paper/2006.09882/) (2020)
- [Improved Baselines with Momentum Contrastive Learning](https://mlsanity.com/paper/2003.04297/) (2020)
- [Learning deep representations by mutual information estimation and maximization](https://mlsanity.com/paper/1808.06670/) (2018)
- [VICReg: Variance-Invariance-Covariance Regularization for Self-Supervised Learning](https://mlsanity.com/paper/2105.04906/) (2021)
- [Challenging Common Assumptions in the Unsupervised Learning of Disentangled Representations](https://mlsanity.com/paper/1811.12359/) (2018)
- [Maximum Classifier Discrepancy for Unsupervised Domain Adaptation](https://mlsanity.com/paper/1712.02560/) (2017)
- [MINE: Mutual Information Neural Estimation](https://mlsanity.com/paper/1801.04062/) (2018)
- [Deep Visual Domain Adaptation: A Survey](https://mlsanity.com/paper/1802.03601/) (2018)
- [Semi-Supervised Learning with Deep Generative Models](https://mlsanity.com/paper/1406.5298/) (2014)
- [Adversarial Autoencoders](https://mlsanity.com/paper/1511.05644/) (2015)
- [Time-Series Representation Learning via Temporal and Contextual Contrasting](https://mlsanity.com/paper/2106.14112/) (2021)
- [Unsupervised Domain Adaptation with Residual Transfer Networks](https://mlsanity.com/paper/1602.04433/) (2016)
- [Keystroke Dynamics as Part of Lifelogging](https://mlsanity.com/paper/2010.10144/) (2020)
- [Self-Supervised Learning with Data Augmentations Provably Isolates Content from Style](https://mlsanity.com/paper/2106.04619/) (2021)
- [Contrastive Learning Inverts the Data Generating Process](https://mlsanity.com/paper/2102.08850/) (2021)
- [Neural Style Transfer: A Review](https://mlsanity.com/paper/1705.04058/) (2017)
- [Contrastive Learning of General-Purpose Audio Representations](https://mlsanity.com/paper/2010.10915/) (2020)
- [The Numerics of GANs](https://mlsanity.com/paper/1705.10461/) (2017)
- [Small Data Challenges in Big Data Era: A Survey of Recent Progress on Unsupervised and Semi-Supervised Methods](https://mlsanity.com/paper/1903.11260/) (2019)
- [Condition-Transforming Variational AutoEncoder for Conversation Response Generation](https://mlsanity.com/paper/1904.10610/) (2019)

## Built on by (most cited first, 1 of 1)

- [CLAIRE: Compressed Latent Autoencoder for Industrial Representation and Evaluation -- A Deep Learning Framework for Smart Manufacturing](https://mlsanity.com/paper/2603.06361/) (2026)

## Abstract (arXiv)

Extracting fine-grained features such as styles from unlabeled data is crucial for data analysis. Unsupervised methods such as variational autoencoders (VAEs) can extract styles that are usually mixed with other features. Conditional VAEs (CVAEs) can isolate styles using class labels; however, there are no established methods to extract only styles using unlabeled data. In this paper, we propose a CVAE-based method that extracts style features using only unlabeled data. The proposed model consists of a contrastive learning (CL) part that extracts style-independent features and a CVAE part that extracts style features. The CL model learns representations independent of data augmentation, which can be viewed as a perturbation in styles, in a self-supervised manner. Considering the style-independent features from the pretrained CL model as a condition, the CVAE learns to extract only styles. Additionally, we introduce a constraint based on mutual information between the CL and VAE features to prevent the CVAE from ignoring the condition. Experiments conducted using two simple datasets, MNIST and an original dataset based on Google Fonts, demonstrate that the proposed method can efficiently extract style features. Further experiments using real-world natural image datasets were also conducted to illustrate the method's extendability.