# Disentangling Factors of Variation with Cycle-Consistent Variational Auto-Encoders

arXiv: https://arxiv.org/abs/1804.10469 · HTML: https://mlsanity.com/paper/1804.10469/

## Key facts

- Cited by 49 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 27 Apr 2018.

## Built on by (most cited first, 30 of 49)

- [ImageBART: Bidirectional Context with Multinomial Diffusion for Autoregressive Image Synthesis](https://mlsanity.com/paper/2108.08827/) (2021)
- [Domain Adaptation In Reinforcement Learning Via Latent Unified State Representation](https://mlsanity.com/paper/2102.05714/) (2021)
- [Orthogonal Jacobian Regularization for Unsupervised Disentanglement in Image Generation](https://mlsanity.com/paper/2108.07668/) (2021)
- [Video Autoencoder: self-supervised disentanglement of static 3D structure and motion](https://mlsanity.com/paper/2110.02951/) (2021)
- [StyleFusion: A Generative Model for Disentangling Spatial Segments](https://mlsanity.com/paper/2107.07437/) (2021)
- [Math Word Problem Generation with Mathematical Consistency and Problem Context Constraints](https://mlsanity.com/paper/2109.04546/) (2021)
- [ICAM-reg: Interpretable Classification and Regression with Feature Attribution for Mapping Neurological Phenotypes in Individual Scans](https://mlsanity.com/paper/2103.02561/) (2021)
- [Scaling-up Disentanglement for Image Translation](https://mlsanity.com/paper/2103.14017/) (2021)
- [Behavior-Driven Synthesis of Human Dynamics](https://mlsanity.com/paper/2103.04677/) (2021)
- [A Contrastive Objective for Learning Disentangled Representations](https://mlsanity.com/paper/2203.11284/) (2022)
- [Zero-shot Imitation Learning from Demonstrations for Legged Robot Visual Navigation](https://mlsanity.com/paper/1909.12971/) (2019)
- [Disentangling A Single MR Modality](https://mlsanity.com/paper/2205.04982/) (2022)
- [Gacs-Korner Common Information Variational Autoencoder](https://mlsanity.com/paper/2205.12239/) (2022)
- [Multi-objective Deep Data Generation with Correlated Property Control](https://mlsanity.com/paper/2210.01796/) (2022)
- [MonoNeRF: Learning Generalizable NeRFs from Monocular Videos without Camera Pose](https://mlsanity.com/paper/2210.07181/) (2022)
- [TUVF: Learning Generalizable Texture UV Radiance Fields](https://mlsanity.com/paper/2305.03040/) (2023)
- [Sill-Net: Feature Augmentation with Separated Illumination Representation](https://mlsanity.com/paper/2102.03539/) (2021)
- [Rethinking Content and Style: Exploring Bias for Unsupervised Disentanglement](https://mlsanity.com/paper/2102.10544/) (2021)
- [Weakly Supervised Correspondence Learning](https://mlsanity.com/paper/2203.00904/) (2022)
- [Retriever: Learning Content-Style Representation as a Token-Level Bipartite Graph](https://mlsanity.com/paper/2202.12307/) (2022)
- [Latent Space Bayesian Optimization with Latent Data Augmentation for Enhanced Exploration](https://mlsanity.com/paper/2302.02399/) (2023)
- [Controllable Data Augmentation Through Deep Relighting](https://mlsanity.com/paper/2110.13996/) (2021)
- [Learning Invariances with Generalised Input-Convex Neural Networks](https://mlsanity.com/paper/2204.07009/) (2022)
- [A robust estimator of mutual information for deep learning interpretability](https://mlsanity.com/paper/2211.00024/) (2022)
- [Automaton Distillation: Neuro-Symbolic Transfer Learning for Deep Reinforcement Learning](https://mlsanity.com/paper/2310.19137/) (2023)
- [Learning ABCs: Approximate Bijective Correspondence for isolating factors of variation with weak supervision](https://mlsanity.com/paper/2103.03240/) (2021)
- [Learning Conditional Invariance through Cycle Consistency](https://mlsanity.com/paper/2111.13185/) (2021)
- [Red PANDA: Disambiguating Anomaly Detection by Removing Nuisance Factors](https://mlsanity.com/paper/2207.03478/) (2022)
- [Symbolic Disentangled Representations for Images](https://mlsanity.com/paper/2412.19847/) (2024)
- [Disentangled Representation Learning for Astronomical Chemical Tagging](https://mlsanity.com/paper/2103.06377/) (2021)

## Abstract (arXiv)

Generative models that learn disentangled representations for different factors of variation in an image can be very useful for targeted data augmentation. By sampling from the disentangled latent subspace of interest, we can efficiently generate new data necessary for a particular task. Learning disentangled representations is a challenging problem, especially when certain factors of variation are difficult to label. In this paper, we introduce a novel architecture that disentangles the latent space into two complementary subspaces by using only weak supervision in form of pairwise similarity labels. Inspired by the recent success of cycle-consistent adversarial architectures, we use cycle-consistency in a variational auto-encoder framework. Our non-adversarial approach is in contrast with the recent works that combine adversarial training with auto-encoders to disentangle representations. We show compelling results of disentangled latent subspaces on three datasets and compare with recent works that leverage adversarial training.