# Disentangling Autoencoders (DAE)

arXiv: https://arxiv.org/abs/2202.09926 · HTML: https://mlsanity.com/paper/2202.09926/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 28 of its 59 references that are in the map.
- First posted on arXiv 20 Feb 2022.

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

- [Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift](https://mlsanity.com/paper/1502.03167/) (2015)
- [Auto-Encoding Variational Bayes](https://mlsanity.com/paper/1312.6114/) (2013)
- [Deep Learning Face Attributes in the Wild](https://mlsanity.com/paper/1411.7766/) (2014)
- [Variational Inference with Normalizing Flows](https://mlsanity.com/paper/1505.05770/) (2015)
- [Disentangling by Factorising](https://mlsanity.com/paper/1802.05983/) (2018)
- [Wasserstein Auto-Encoders](https://mlsanity.com/paper/1711.01558/) (2017)
- [Interpretable Machine Learning: Fundamental Principles and 10 Grand Challenges](https://mlsanity.com/paper/2103.11251/) (2021)
- [Understanding disentangling in β-VAE](https://mlsanity.com/paper/1804.03599/) (2018)
- [Towards a Definition of Disentangled Representations](https://mlsanity.com/paper/1812.02230/) (2018)
- [VAE with a VampPrior](https://mlsanity.com/paper/1705.07120/) (2017)
- [Isolating Sources of Disentanglement in Variational Autoencoders](https://mlsanity.com/paper/1802.04942/) (2018)
- [Recent Advances in Autoencoder-Based Representation Learning](https://mlsanity.com/paper/1812.05069/) (2018)
- [Discovering physical concepts with neural networks](https://mlsanity.com/paper/1807.10300/) (2018)
- [Learning Deep Disentangled Embeddings with the F-Statistic Loss](https://mlsanity.com/paper/1802.05312/) (2018)
- [Counterfactual Zero-Shot and Open-Set Visual Recognition](https://mlsanity.com/paper/2103.00887/) (2021)
- [Understanding and Improving Interpolation in Autoencoders via an Adversarial Regularizer](https://mlsanity.com/paper/1807.07543/) (2018)
- [Measuring Disentanglement: A Review of Metrics](https://mlsanity.com/paper/2012.09276/) (2020)
- [A Contrastive Learning Approach for Training Variational Autoencoder Priors](https://mlsanity.com/paper/2010.02917/) (2020)
- [Do 2D GANs Know 3D Shape? Unsupervised 3D shape reconstruction from 2D Image GANs](https://mlsanity.com/paper/2011.00844/) (2020)
- [Disentangling Factors of Variation Using Few Labels](https://mlsanity.com/paper/1905.01258/) (2019)
- [Theory and Evaluation Metrics for Learning Disentangled Representations](https://mlsanity.com/paper/1908.09961/) (2019)
- [Learning Independent Features with Adversarial Nets for Non-linear ICA](https://mlsanity.com/paper/1710.05050/) (2017)
- [Variational Autoencoder with Implicit Optimal Priors](https://mlsanity.com/paper/1809.05284/) (2018)
- [Unsupervised deep learning identifies semantic disentanglement in single inferotemporal neurons](https://mlsanity.com/paper/2006.14304/) (2020)
- [Balancing reconstruction error and Kullback-Leibler divergence in Variational Autoencoders](https://mlsanity.com/paper/2002.07514/) (2020)
- [A Survey of Inductive Biases for Factorial Representation-Learning](https://mlsanity.com/paper/1612.05299/) (2016)
- [Perceptual Generative Autoencoders](https://mlsanity.com/paper/1906.10335/) (2019)
- [Non-linear ICA based on Cramer-Wold metric](https://mlsanity.com/paper/1903.00201/) (2019)

## Built on by (most cited first, 3 of 3)

- [Robust Anomaly Detection through Multi-Modal Autoencoder Fusion for Small Vehicle Damage Detection](https://mlsanity.com/paper/2509.01719/) (2025)
- [Intrinsic Dimension Estimating Autoencoder (IDEA) Using CancelOut Layer and a Projected Loss](https://mlsanity.com/paper/2509.10011/) (2025)
- [StyleAutoEncoder for manipulating image attributes using pre-trained StyleGAN](https://mlsanity.com/paper/2412.20164/) (2024)

## Abstract (arXiv)

Noting the importance of factorizing (or disentangling) the latent space, we propose a novel, non-probabilistic disentangling framework for autoencoders, based on the principles of symmetry transformations in group-theory. To the best of our knowledge, this is the first deterministic model that is aiming to achieve disentanglement based on autoencoders without regularizers. The proposed model is compared to seven state-of-the-art generative models based on autoencoders and evaluated based on five supervised disentanglement metrics. The experimental results show that the proposed model can have better disentanglement when variances of each features are different. We believe that this model leads to a new field for disentanglement learning based on autoencoders without regularizers.