# Demystifying Inter-Class Disentanglement

arXiv: https://arxiv.org/abs/1906.11796 · HTML: https://mlsanity.com/paper/1906.11796/

## Key facts

- Cited by 31 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 27 Jun 2019.

## Built on by (most cited first, 30 of 31)

- [Text2Performer: Text-Driven Human Video Generation](https://mlsanity.com/paper/2304.08483/) (2023)
- [Semi-Supervised and Unsupervised Deep Visual Learning: A Survey](https://mlsanity.com/paper/2208.11296/) (2022)
- [Learning Disentangled Representations in the Imaging Domain](https://mlsanity.com/paper/2108.12043/) (2021)
- [Predict, Prevent, and Evaluate: Disentangled Text-Driven Image Manipulation Empowered by Pre-Trained Vision-Language Model](https://mlsanity.com/paper/2111.13333/) (2021)
- [An Image is Worth More Than a Thousand Words: Towards Disentanglement in the Wild](https://mlsanity.com/paper/2106.15610/) (2021)
- [GAN-based Facial Attribute Manipulation](https://mlsanity.com/paper/2210.12683/) (2022)
- [Scaling-up Disentanglement for Image Translation](https://mlsanity.com/paper/2103.14017/) (2021)
- [A Contrastive Objective for Learning Disentangled Representations](https://mlsanity.com/paper/2203.11284/) (2022)
- [Controllable cardiac synthesis via disentangled anatomy arithmetic](https://mlsanity.com/paper/2107.01748/) (2021)
- [Rethinking Content and Style: Exploring Bias for Unsupervised Disentanglement](https://mlsanity.com/paper/2102.10544/) (2021)
- [SAIC: Integration of Speech Anonymization and Identity Classification](https://mlsanity.com/paper/2312.15190/) (2023)
- [Disentangled Neural Relational Inference for Interpretable Motion Prediction](https://mlsanity.com/paper/2401.03599/) (2024)
- [VDSM: Unsupervised Video Disentanglement with State-Space Modeling and Deep Mixtures of Experts](https://mlsanity.com/paper/2103.07292/) (2021)
- [DisUnknown: Distilling Unknown Factors for Disentanglement Learning](https://mlsanity.com/paper/2109.08090/) (2021)
- [Retriever: Learning Content-Style Representation as a Token-Level Bipartite Graph](https://mlsanity.com/paper/2202.12307/) (2022)
- [Sequential Representation Learning via Static-Dynamic Conditional Disentanglement](https://mlsanity.com/paper/2408.05599/) (2024)
- [Learning ABCs: Approximate Bijective Correspondence for isolating factors of variation with weak supervision](https://mlsanity.com/paper/2103.03240/) (2021)
- [CoDeGAN: Contrastive Disentanglement for Generative Adversarial Network](https://mlsanity.com/paper/2103.03636/) (2021)
- [Red PANDA: Disambiguating Anomaly Detection by Removing Nuisance Factors](https://mlsanity.com/paper/2207.03478/) (2022)
- [A Novel Information-Theoretic Objective to Disentangle Representations for Fair Classification](https://mlsanity.com/paper/2310.13990/) (2023)
- [Label Augmentation for Neural Networks Robustness](https://mlsanity.com/paper/2408.01977/) (2024)
- [Marginal Matching Does Not License Factorized Sampling: Auditing Conditional Style Leakage in Factorized Generative Models](https://mlsanity.com/paper/2608.05243/) (2026)
- [Towards Disentangling Information Paths with Coded ResNeXt](https://mlsanity.com/paper/2202.05343/) (2022)
- [Generative Modeling Helps Weak Supervision (and Vice Versa)](https://mlsanity.com/paper/2203.12023/) (2022)
- [D-LORD for Motion Stylization](https://mlsanity.com/paper/2412.04097/) (2024)
- [Disentanglement in Difference: Directly Learning Semantically Disentangled Representations by Maximizing Inter-Factor Differences](https://mlsanity.com/paper/2502.03123/) (2025)
- [Generative Fields: Uncovering Hierarchical Feature Control for StyleGAN via Inverted Receptive Fields](https://mlsanity.com/paper/2504.17712/) (2025)
- [Learning Private Representations through Entropy-based Adversarial Training](https://mlsanity.com/paper/2507.10194/) (2025)
- [DiLO: Disentangled Latent Optimization for Learning Shape and Deformation in Grouped Deforming 3D Objects](https://mlsanity.com/paper/2511.06115/) (2025)
- [Retrieval-Augmented Gaussian Avatars: Improving Expression Generalization](https://mlsanity.com/paper/2603.08645/) (2026)

## Abstract (arXiv)

Learning to disentangle the hidden factors of variations within a set of observations is a key task for artificial intelligence. We present a unified formulation for class and content disentanglement and use it to illustrate the limitations of current methods. We therefore introduce LORD, a novel method based on Latent Optimization for Representation Disentanglement. We find that latent optimization, along with an asymmetric noise regularization, is superior to amortized inference for achieving disentangled representations. In extensive experiments, our method is shown to achieve better disentanglement performance than both adversarial and non-adversarial methods that use the same level of supervision. We further introduce a clustering-based approach for extending our method for settings that exhibit in-class variation with promising results on the task of domain translation.