# Rethinking Content and Style: Exploring Bias for Unsupervised Disentanglement arXiv: https://arxiv.org/abs/2102.10544 ยท HTML: https://mlsanity.com/paper/2102.10544/ ## Key facts - Cited by 7 papers in the map (data through 14 Oct 2026). - Builds on 31 of its 50 references that are in the map. - First posted on arXiv 21 Feb 2021. ## Builds on (most cited first, 30 of 31) - [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) - [Very Deep Convolutional Networks for Large-Scale Image Recognition](https://mlsanity.com/paper/1409.1556/) (2014) - [The Unreasonable Effectiveness of Deep Features as a Perceptual Metric](https://mlsanity.com/paper/1801.03924/) (2018) - [A Style-Based Generator Architecture for Generative Adversarial Networks](https://mlsanity.com/paper/1812.04948/) (2018) - [Deep Learning Face Attributes in the Wild](https://mlsanity.com/paper/1411.7766/) (2014) - [Analyzing and Improving the Image Quality of StyleGAN](https://mlsanity.com/paper/1912.04958/) (2019) - [Arbitrary Style Transfer in Real-time with Adaptive Instance Normalization](https://mlsanity.com/paper/1703.06868/) (2017) - [Unsupervised Feature Learning via Non-Parametric Instance-level Discrimination](https://mlsanity.com/paper/1805.01978/) (2018) - [Glow: Generative Flow with Invertible 1x1 Convolutions](https://mlsanity.com/paper/1807.03039/) (2018) - [Challenging Common Assumptions in the Unsupervised Learning of Disentangled Representations](https://mlsanity.com/paper/1811.12359/) (2018) - [Multimodal Unsupervised Image-to-Image Translation](https://mlsanity.com/paper/1804.04732/) (2018) - [Disentangling by Factorising](https://mlsanity.com/paper/1802.05983/) (2018) - [How far are we from solving the 2D & 3D Face Alignment problem? (and a dataset of 230,000 3D facial landmarks)](https://mlsanity.com/paper/1703.07332/) (2017) - [Few-Shot Unsupervised Image-to-Image Translation](https://mlsanity.com/paper/1905.01723/) (2019) - [Swapping Autoencoder for Deep Image Manipulation](https://mlsanity.com/paper/2007.00653/) (2020) - [Unsupervised Learning of Probably Symmetric Deformable 3D Objects from Images in the Wild](https://mlsanity.com/paper/1911.11130/) (2019) - [Pix2Vox: Context-aware 3D Reconstruction from Single and Multi-view Images](https://mlsanity.com/paper/1901.11153/) (2019) - [Optimizing the Latent Space of Generative Networks](https://mlsanity.com/paper/1707.05776/) (2017) - [Demystifying Neural Style Transfer](https://mlsanity.com/paper/1701.01036/) (2017) - [Unsupervised Learning of Disentangled Representations from Video](https://mlsanity.com/paper/1705.10915/) (2017) - [Combining Markov Random Fields and Convolutional Neural Networks for Image Synthesis](https://mlsanity.com/paper/1601.04589/) (2016) - [Multi-Level Variational Autoencoder: Learning Disentangled Representations from Grouped Observations](https://mlsanity.com/paper/1705.08841/) (2017) - [Disentangling factors of variation in deep representations using adversarial training](https://mlsanity.com/paper/1611.03383/) (2016) - [Disentangling Factors of Variation with Cycle-Consistent Variational Auto-Encoders](https://mlsanity.com/paper/1804.10469/) (2018) - [MVF-Net: Multi-View 3D Face Morphable Model Regression](https://mlsanity.com/paper/1904.04473/) (2019) - [Cross-Dataset Person Re-Identification via Unsupervised Pose Disentanglement and Adaptation](https://mlsanity.com/paper/1909.09675/) (2019) - [TransGaGa: Geometry-Aware Unsupervised Image-to-Image Translation](https://mlsanity.com/paper/1904.09571/) (2019) - [Demystifying Inter-Class Disentanglement](https://mlsanity.com/paper/1906.11796/) (2019) - [Challenges in Disentangling Independent Factors of Variation](https://mlsanity.com/paper/1711.02245/) (2017) ## Built on by (most cited first, 7 of 7) - [StyleDiffusion: Controllable Disentangled Style Transfer via Diffusion Models](https://mlsanity.com/paper/2308.07863/) (2023) - [Simple Disentanglement of Style and Content in Visual Representations](https://mlsanity.com/paper/2302.09795/) (2023) - [PEER pressure: Model-to-Model Regularization for Single Source Domain Generalization](https://mlsanity.com/paper/2505.12745/) (2025) - [Retriever: Learning Content-Style Representation as a Token-Level Bipartite Graph](https://mlsanity.com/paper/2202.12307/) (2022) - [Unsupervised Disentanglement of Content and Style via Variance-Invariance Constraints](https://mlsanity.com/paper/2407.03824/) (2024) - [DualContrast: Unsupervised Disentangling of Content and Transformations with Implicit Parameterization](https://mlsanity.com/paper/2405.16796/) (2024) - [Task-Relevant Representation Decoupling for Visual Reinforcement Learning Generalization](https://mlsanity.com/paper/2607.00796/) (2026) ## Abstract (arXiv) Content and style (C-S) disentanglement intends to decompose the underlying explanatory factors of objects into two independent subspaces. From the unsupervised disentanglement perspective, we rethink content and style and propose a formulation for unsupervised C-S disentanglement based on our assumption that different factors are of different importance and popularity for image reconstruction, which serves as a data bias. The corresponding model inductive bias is introduced by our proposed C-S disentanglement Module (C-S DisMo), which assigns different and independent roles to content and style when approximating the real data distributions. Specifically, each content embedding from the dataset, which encodes the most dominant factors for image reconstruction, is assumed to be sampled from a shared distribution across the dataset. The style embedding for a particular image, encoding the remaining factors, is used to customize the shared distribution through an affine transformation. The experiments on several popular datasets demonstrate that our method achieves the state-of-the-art unsupervised C-S disentanglement, which is comparable or even better than supervised methods. We verify the effectiveness of our method by downstream tasks: domain translation and single-view 3D reconstruction. Project page at https://github.com/xrenaa/CS-DisMo.