# Toward a Visual Concept Vocabulary for GAN Latent Space

arXiv: https://arxiv.org/abs/2110.04292 · HTML: https://mlsanity.com/paper/2110.04292/

## Key facts

- Cited by 15 papers in the map (data through 14 Oct 2026).
- Builds on 21 of its 28 references that are in the map.
- First posted on arXiv 8 Oct 2021.

## Builds on (most cited first, 21 of 21)

- [A Style-Based Generator Architecture for Generative Adversarial Networks](https://mlsanity.com/paper/1812.04948/) (2018)
- [BERTScore: Evaluating Text Generation with BERT](https://mlsanity.com/paper/1904.09675/) (2019)
- [Large Scale GAN Training for High Fidelity Natural Image Synthesis](https://mlsanity.com/paper/1809.11096/) (2018)
- [Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networks](https://mlsanity.com/paper/1511.06434/) (2015)
- [Semantic Image Synthesis with Spatially-Adaptive Normalization](https://mlsanity.com/paper/1903.07291/) (2019)
- [Unified Perceptual Parsing for Scene Understanding](https://mlsanity.com/paper/1807.10221/) (2018)
- [Interpreting the Latent Space of GANs for Semantic Face Editing](https://mlsanity.com/paper/1907.10786/) (2019)
- [GANSpace: Discovering Interpretable GAN Controls](https://mlsanity.com/paper/2004.02546/) (2020)
- [Closed-Form Factorization of Latent Semantics in GANs](https://mlsanity.com/paper/2007.06600/) (2020)
- [Generative Visual Manipulation on the Natural Image Manifold](https://mlsanity.com/paper/1609.03552/) (2016)
- [StyleSpace Analysis: Disentangled Controls for StyleGAN Image Generation](https://mlsanity.com/paper/2011.12799/) (2020)
- [Unsupervised Discovery of Interpretable Directions in the GAN Latent Space](https://mlsanity.com/paper/2002.03754/) (2020)
- [On the "steerability" of generative adversarial networks](https://mlsanity.com/paper/1907.07171/) (2019)
- [GANalyze: Toward Visual Definitions of Cognitive Image Properties](https://mlsanity.com/paper/1906.10112/) (2019)
- [Semantic Photo Manipulation with a Generative Image Prior](https://mlsanity.com/paper/2005.07727/) (2020)
- [Seeing What a GAN Cannot Generate](https://mlsanity.com/paper/1910.11626/) (2019)
- [Semantic Hierarchy Emerges in Deep Generative Representations for Scene Synthesis](https://mlsanity.com/paper/1911.09267/) (2019)
- [Controlling generative models with continuous factors of variations](https://mlsanity.com/paper/2001.10238/) (2020)
- [The Hessian Penalty: A Weak Prior for Unsupervised Disentanglement](https://mlsanity.com/paper/2008.10599/) (2020)
- [Image Counterfactual Sensitivity Analysis for Detecting Unintended Bias](https://mlsanity.com/paper/1906.06439/) (2019)
- [Latent Compass: Creation by Navigation](https://mlsanity.com/paper/2012.14283/) (2020)

## Built on by (most cited first, 15 of 15)

- [Natural Language Descriptions of Deep Visual Features](https://mlsanity.com/paper/2201.11114/) (2022)
- [Tell Your Model Where to Attend: Post-hoc Attention Steering for LLMs](https://mlsanity.com/paper/2311.02262/) (2023)
- [A Multimodal Automated Interpretability Agent](https://mlsanity.com/paper/2404.14394/) (2024)
- [Explaining black box text modules in natural language with language models](https://mlsanity.com/paper/2305.09863/) (2023)
- [PromptPaint: Steering Text-to-Image Generation Through Paint Medium-like Interactions](https://mlsanity.com/paper/2308.05184/) (2023)
- [Name Your Style: An Arbitrary Artist-aware Image Style Transfer](https://mlsanity.com/paper/2202.13562/) (2022)
- [On the Exploitation of Deepfake Model Recognition](https://mlsanity.com/paper/2204.04513/) (2022)
- [Crafting Interpretable Embeddings by Asking LLMs Questions](https://mlsanity.com/paper/2405.16714/) (2024)
- [End-to-End Visual Editing with a Generatively Pre-Trained Artist](https://mlsanity.com/paper/2205.01668/) (2022)
- [A Survey on Leveraging Pre-trained Generative Adversarial Networks for Image Editing and Restoration](https://mlsanity.com/paper/2207.10309/) (2022)
- [Discovering Class-Specific GAN Controls for Semantic Image Synthesis](https://mlsanity.com/paper/2212.01455/) (2022)
- [3D GANs and Latent Space: A comprehensive survey](https://mlsanity.com/paper/2304.03932/) (2023)
- [CAST-LUT: Tokenizer-Guided HSV Look-Up Tables for Purple Flare Removal](https://mlsanity.com/paper/2511.06764/) (2025)
- [Bridging Text and Image for Artist Style Transfer via Contrastive Learning](https://mlsanity.com/paper/2410.09566/) (2024)
- [RankT2I: A Submodular Framework for Discovering Interpretable and Diverse Semantics in Text-to-Image Models](https://mlsanity.com/paper/2608.14226/) (2026)

## Abstract (arXiv)

A large body of recent work has identified transformations in the latent spaces of generative adversarial networks (GANs) that consistently and interpretably transform generated images. But existing techniques for identifying these transformations rely on either a fixed vocabulary of pre-specified visual concepts, or on unsupervised disentanglement techniques whose alignment with human judgments about perceptual salience is unknown. This paper introduces a new method for building open-ended vocabularies of primitive visual concepts represented in a GAN's latent space. Our approach is built from three components: (1) automatic identification of perceptually salient directions based on their layer selectivity; (2) human annotation of these directions with free-form, compositional natural language descriptions; and (3) decomposition of these annotations into a visual concept vocabulary, consisting of distilled directions labeled with single words. Experiments show that concepts learned with our approach are reliable and composable -- generalizing across classes, contexts, and observers, and enabling fine-grained manipulation of image style and content.