# An Image is Worth More Than a Thousand Words: Towards Disentanglement in the Wild

arXiv: https://arxiv.org/abs/2106.15610 · HTML: https://mlsanity.com/paper/2106.15610/

## Key facts

- Cited by 30 papers in the map (data through 14 Oct 2026).
- Builds on 36 of its 46 references that are in the map.
- First posted on arXiv 29 Jun 2021.

## Builds on (most cited first, 30 of 36)

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [A Style-Based Generator Architecture for Generative Adversarial Networks](https://mlsanity.com/paper/1812.04948/) (2018)
- [Zero-Shot Text-to-Image Generation](https://mlsanity.com/paper/2102.12092/) (2021)
- [Analyzing and Improving the Image Quality of StyleGAN](https://mlsanity.com/paper/1912.04958/) (2019)
- [StarGAN v2: Diverse Image Synthesis for Multiple Domains](https://mlsanity.com/paper/1912.01865/) (2019)
- [StyleCLIP: Text-Driven Manipulation of StyleGAN Imagery](https://mlsanity.com/paper/2103.17249/) (2021)
- [Challenging Common Assumptions in the Unsupervised Learning of Disentangled Representations](https://mlsanity.com/paper/1811.12359/) (2018)
- [CNN-generated images are surprisingly easy to spot... for now](https://mlsanity.com/paper/1912.11035/) (2019)
- [Disentangling by Factorising](https://mlsanity.com/paper/1802.05983/) (2018)
- [Semi-Supervised Learning with Deep Generative Models](https://mlsanity.com/paper/1406.5298/) (2014)
- [StyleSpace Analysis: Disentangled Controls for StyleGAN Image Generation](https://mlsanity.com/paper/2011.12799/) (2020)
- [Variational Inference of Disentangled Latent Concepts from Unlabeled Observations](https://mlsanity.com/paper/1711.00848/) (2017)
- [Contrastive Learning Inverts the Data Generating Process](https://mlsanity.com/paper/2102.08850/) (2021)
- [Flexibly Fair Representation Learning by Disentanglement](https://mlsanity.com/paper/1906.02589/) (2019)
- [Isolating Sources of Disentanglement in Variational Autoencoders](https://mlsanity.com/paper/1802.04942/) (2018)
- [Learning Visual Features from Large Weakly Supervised Data](https://mlsanity.com/paper/1511.02251/) (2015)
- [On the Fairness of Disentangled Representations](https://mlsanity.com/paper/1905.13662/) (2019)
- [Unsupervised Learning of Disentangled Representations from Video](https://mlsanity.com/paper/1705.10915/) (2017)
- [Visual Object Networks: Image Generation with Disentangled 3D Representation](https://mlsanity.com/paper/1812.02725/) (2018)
- [Fairness in Deep Learning: A Computational Perspective](https://mlsanity.com/paper/1908.08843/) (2019)
- [Learning Visual Representations with Caption Annotations](https://mlsanity.com/paper/2008.01392/) (2020)
- [Towards Nonlinear Disentanglement in Natural Data with Temporal Sparse Coding](https://mlsanity.com/paper/2007.10930/) (2020)
- [Domain Agnostic Learning with Disentangled Representations](https://mlsanity.com/paper/1904.12347/) (2019)
- [Paint by Word](https://mlsanity.com/paper/2103.10951/) (2021)
- [Multi-Level Variational Autoencoder: Learning Disentangled Representations from Grouped Observations](https://mlsanity.com/paper/1705.08841/) (2017)
- [Are Disentangled Representations Helpful for Abstract Visual Reasoning?](https://mlsanity.com/paper/1905.12506/) (2019)
- [Webly Supervised Learning of Convolutional Networks](https://mlsanity.com/paper/1505.01554/) (2015)
- [Unsupervised Learning of Disentangled and Interpretable Representations from Sequential Data](https://mlsanity.com/paper/1709.07902/) (2017)
- [A causal view of compositional zero-shot recognition](https://mlsanity.com/paper/2006.14610/) (2020)
- [Disentangling Factors of Variation Using Few Labels](https://mlsanity.com/paper/1905.01258/) (2019)

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

- [Exploring CLIP for Assessing the Look and Feel of Images](https://mlsanity.com/paper/2207.12396/) (2022)
- [GlanceNets: Interpretabile, Leak-proof Concept-based Models](https://mlsanity.com/paper/2205.15612/) (2022)
- [ObjectDrop: Bootstrapping Counterfactuals for Photorealistic Object Removal and Insertion](https://mlsanity.com/paper/2403.18818/) (2024)
- [Controllable and Compositional Generation with Latent-Space Energy-Based Models](https://mlsanity.com/paper/2110.10873/) (2021)
- [Predict, Prevent, and Evaluate: Disentangled Text-Driven Image Manipulation Empowered by Pre-Trained Vision-Language Model](https://mlsanity.com/paper/2111.13333/) (2021)
- [Bootstrapping Multi-view Representations for Fake News Detection](https://mlsanity.com/paper/2206.05741/) (2022)
- [Training-free Zero-shot Composed Image Retrieval with Local Concept Reranking](https://mlsanity.com/paper/2312.08924/) (2023)
- [Interpretability is in the Mind of the Beholder: A Causal Framework for Human-interpretable Representation Learning](https://mlsanity.com/paper/2309.07742/) (2023)
- [On the Versatile Uses of Partial Distance Correlation in Deep Learning](https://mlsanity.com/paper/2207.09684/) (2022)
- [CLIP-PAE: Projection-Augmentation Embedding to Extract Relevant Features for a Disentangled, Interpretable, and Controllable Text-Guided Face Manipulation](https://mlsanity.com/paper/2210.03919/) (2022)
- [MeLFusion: Synthesizing Music from Image and Language Cues using Diffusion Models](https://mlsanity.com/paper/2406.04673/) (2024)
- [clip2latent: Text driven sampling of a pre-trained StyleGAN using denoising diffusion and CLIP](https://mlsanity.com/paper/2210.02347/) (2022)
- [De-Diffusion Makes Text a Strong Cross-Modal Interface](https://mlsanity.com/paper/2311.00618/) (2023)
- [A Survey of Methods, Challenges and Perspectives in Causality](https://mlsanity.com/paper/2302.00293/) (2023)
- [Leveraging Relational Information for Learning Weakly Disentangled Representations](https://mlsanity.com/paper/2205.10056/) (2022)
- [Retrieval-based Disentangled Representation Learning with Natural Language Supervision](https://mlsanity.com/paper/2212.07699/) (2022)
- [Towards Identifiable Unsupervised Domain Translation: A Diversified Distribution Matching Approach](https://mlsanity.com/paper/2401.09671/) (2024)
- [Highlighting What Matters: Promptable Embeddings for Attribute-Focused Image Retrieval](https://mlsanity.com/paper/2505.15877/) (2025)
- [SKADA-Bench: Benchmarking Unsupervised Domain Adaptation Methods with Realistic Validation On Diverse Modalities](https://mlsanity.com/paper/2407.11676/) (2024)
- [Disentanglement of Latent Representations via Causal Interventions](https://mlsanity.com/paper/2302.00869/) (2023)
- [Improving Diversity in Zero-Shot GAN Adaptation with Semantic Variations](https://mlsanity.com/paper/2308.10554/) (2023)
- [MM-SeR: Multimodal Self-Refinement for Lightweight Image Captioning](https://mlsanity.com/paper/2508.21451/) (2025)
- [Selective manipulation of disentangled representations for privacy-aware facial image processing](https://mlsanity.com/paper/2208.12632/) (2022)
- [Modular Representations for Weak Disentanglement](https://mlsanity.com/paper/2209.05336/) (2022)
- [Simple Primitives with Feasibility- and Contextuality-Dependence for Open-World Compositional Zero-shot Learning](https://mlsanity.com/paper/2211.02895/) (2022)
- [Robust Domain Generalisation with Causal Invariant Bayesian Neural Networks](https://mlsanity.com/paper/2410.06349/) (2024)
- [D-LORD for Motion Stylization](https://mlsanity.com/paper/2412.04097/) (2024)
- [What's in Common? Multimodal Models Hallucinate When Reasoning Across Scenes](https://mlsanity.com/paper/2511.03768/) (2025)
- [Domain Transfer Becomes Identifiable via a Single Alignment](https://mlsanity.com/paper/2605.17918/) (2026)
- [Unsupervised Disentanglement Without Compromises : How Functional Orthogonality Enforces Identifiability](https://mlsanity.com/paper/2606.21385/) (2026)

## Abstract (arXiv)

Unsupervised disentanglement has been shown to be theoretically impossible without inductive biases on the models and the data. As an alternative approach, recent methods rely on limited supervision to disentangle the factors of variation and allow their identifiability. While annotating the true generative factors is only required for a limited number of observations, we argue that it is infeasible to enumerate all the factors of variation that describe a real-world image distribution. To this end, we propose a method for disentangling a set of factors which are only partially labeled, as well as separating the complementary set of residual factors that are never explicitly specified. Our success in this challenging setting, demonstrated on synthetic benchmarks, gives rise to leveraging off-the-shelf image descriptors to partially annotate a subset of attributes in real image domains (e.g. of human faces) with minimal manual effort. Specifically, we use a recent language-image embedding model (CLIP) to annotate a set of attributes of interest in a zero-shot manner and demonstrate state-of-the-art disentangled image manipulation results.