# Disentangled Representations from Non-Disentangled Models

arXiv: https://arxiv.org/abs/2102.06204 · HTML: https://mlsanity.com/paper/2102.06204/

## Key facts

- Cited by 13 papers in the map (data through 14 Oct 2026).
- Builds on 39 of its 53 references that are in the map.
- First posted on arXiv 11 Feb 2021.

## Builds on (most cited first, 30 of 39)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [A Style-Based Generator Architecture for Generative Adversarial Networks](https://mlsanity.com/paper/1812.04948/) (2018)
- [Auto-Encoding Variational Bayes](https://mlsanity.com/paper/1312.6114/) (2013)
- [Analyzing and Improving the Image Quality of StyleGAN](https://mlsanity.com/paper/1912.04958/) (2019)
- [Progressive Growing of GANs for Improved Quality, Stability, and Variation](https://mlsanity.com/paper/1710.10196/) (2017)
- [Variational Inference with Normalizing Flows](https://mlsanity.com/paper/1505.05770/) (2015)
- [Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networks](https://mlsanity.com/paper/1511.06434/) (2015)
- [Equality of Opportunity in Supervised Learning](https://mlsanity.com/paper/1610.02413/) (2016)
- [Challenging Common Assumptions in the Unsupervised Learning of Disentangled Representations](https://mlsanity.com/paper/1811.12359/) (2018)
- [Deep Variational Information Bottleneck](https://mlsanity.com/paper/1612.00410/) (2016)
- [InfoGAN: Interpretable Representation Learning by Information Maximizing Generative Adversarial Nets](https://mlsanity.com/paper/1606.03657/) (2016)
- [Counterfactual Fairness](https://mlsanity.com/paper/1703.06856/) (2017)
- [Interpreting the Latent Space of GANs for Semantic Face Editing](https://mlsanity.com/paper/1907.10786/) (2019)
- [Image2StyleGAN: How to Embed Images Into the StyleGAN Latent Space?](https://mlsanity.com/paper/1904.03189/) (2019)
- [Disentangling by Factorising](https://mlsanity.com/paper/1802.05983/) (2018)
- [GANSpace: Discovering Interpretable GAN Controls](https://mlsanity.com/paper/2004.02546/) (2020)
- [In-Domain GAN Inversion for Real Image Editing](https://mlsanity.com/paper/2004.00049/) (2020)
- [Closed-Form Factorization of Latent Semantics in GANs](https://mlsanity.com/paper/2007.06600/) (2020)
- [Fairness Beyond Disparate Treatment & Disparate Impact: Learning Classification without Disparate Mistreatment](https://mlsanity.com/paper/1610.08452/) (2016)
- [Generative Visual Manipulation on the Natural Image Manifold](https://mlsanity.com/paper/1609.03552/) (2016)
- [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)
- [Unsupervised Discovery of Interpretable Directions in the GAN Latent Space](https://mlsanity.com/paper/2002.03754/) (2020)
- [Variational Inference of Disentangled Latent Concepts from Unlabeled Observations](https://mlsanity.com/paper/1711.00848/) (2017)
- [Avoiding Discrimination through Causal Reasoning](https://mlsanity.com/paper/1706.02744/) (2017)
- [Isolating Sources of Disentanglement in Variational Autoencoders](https://mlsanity.com/paper/1802.04942/) (2018)
- [Measuring abstract reasoning in neural networks](https://mlsanity.com/paper/1807.04225/) (2018)
- [On the Fairness of Disentangled Representations](https://mlsanity.com/paper/1905.13662/) (2019)
- [Inverting The Generator Of A Generative Adversarial Network](https://mlsanity.com/paper/1611.05644/) (2016)
- [Recent Advances in Autoencoder-Based Representation Learning](https://mlsanity.com/paper/1812.05069/) (2018)

## Built on by (most cited first, 13 of 13)

- [Disentangled Representation Learning](https://mlsanity.com/paper/2211.11695/) (2022)
- [Learning Disentangled Representation by Exploiting Pretrained Generative Models: A Contrastive Learning View](https://mlsanity.com/paper/2102.10543/) (2021)
- [Not Only Generative Art: Stable Diffusion for Content-Style Disentanglement in Art Analysis](https://mlsanity.com/paper/2304.10278/) (2023)
- [Visual Concepts Tokenization](https://mlsanity.com/paper/2205.10093/) (2022)
- [Latent Transformations via NeuralODEs for GAN-based Image Editing](https://mlsanity.com/paper/2111.14825/) (2021)
- [NaviNeRF: NeRF-based 3D Representation Disentanglement by Latent Semantic Navigation](https://mlsanity.com/paper/2304.11342/) (2023)
- [Disentangling Disentangled Representations: Towards Improved Latent Units via Diffusion Models](https://mlsanity.com/paper/2410.23820/) (2024)
- [Denoising Multi-Beta VAE: Representation Learning for Disentanglement and Generation](https://mlsanity.com/paper/2507.06613/) (2025)
- [Self-supervised Enhancement of Latent Discovery in GANs](https://mlsanity.com/paper/2112.08835/) (2021)
- [Generative Modeling Helps Weak Supervision (and Vice Versa)](https://mlsanity.com/paper/2203.12023/) (2022)
- [Robust GAN inversion](https://mlsanity.com/paper/2308.16510/) (2023)
- [Causality--Delta: Jacobian-Based Dependency Analysis in Flow Matching Models](https://mlsanity.com/paper/2602.02793/) (2026)
- [DisMix: Order-Aware Mixup for Medical Imaging via Disentangling Ordinal and Non-Ordinal Features](https://mlsanity.com/paper/2608.04652/) (2026)

## Abstract (arXiv)

Constructing disentangled representations is known to be a difficult task, especially in the unsupervised scenario. The dominating paradigm of unsupervised disentanglement is currently to train a generative model that separates different factors of variation in its latent space. This separation is typically enforced by training with specific regularization terms in the model's objective function. These terms, however, introduce additional hyperparameters responsible for the trade-off between disentanglement and generation quality. While tuning these hyperparameters is crucial for proper disentanglement, it is often unclear how to tune them without external supervision. This paper investigates an alternative route to disentangled representations. Namely, we propose to extract such representations from the state-of-the-art generative models trained without disentangling terms in their objectives. This paradigm of post hoc disentanglement employs little or no hyperparameters when learning representations while achieving results on par with existing state-of-the-art, as shown by comparison in terms of established disentanglement metrics, fairness, and the abstract reasoning task. All our code and models are publicly available.