# Explaining in Style: Training a GAN to explain a classifier in StyleSpace

arXiv: https://arxiv.org/abs/2104.13369 · HTML: https://mlsanity.com/paper/2104.13369/

## Key facts

- Cited by 122 papers in the map (data through 14 Oct 2026).
- Builds on 33 of its 39 references that are in the map.
- First posted on arXiv 27 Apr 2021.

## Builds on (most cited first, 30 of 33)

- [The Unreasonable Effectiveness of Deep Features as a Perceptual Metric](https://mlsanity.com/paper/1801.03924/) (2018)
- [Explaining and Harnessing Adversarial Examples](https://mlsanity.com/paper/1412.6572/) (2014)
- [Grad-CAM: Visual Explanations from Deep Networks via Gradient-based Localization](https://mlsanity.com/paper/1610.02391/) (2016)
- [A Style-Based Generator Architecture for Generative Adversarial Networks](https://mlsanity.com/paper/1812.04948/) (2018)
- [MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications](https://mlsanity.com/paper/1704.04861/) (2017)
- [Analyzing and Improving the Image Quality of StyleGAN](https://mlsanity.com/paper/1912.04958/) (2019)
- [Learning Important Features Through Propagating Activation Differences](https://mlsanity.com/paper/1704.02685/) (2017)
- [Interpretability Beyond Feature Attribution: Quantitative Testing with Concept Activation Vectors (TCAV)](https://mlsanity.com/paper/1711.11279/) (2017)
- [StarGAN v2: Diverse Image Synthesis for Multiple Domains](https://mlsanity.com/paper/1912.01865/) (2019)
- [Counterfactual Explanations without Opening the Black Box: Automated Decisions and the GDPR](https://mlsanity.com/paper/1711.00399/) (2017)
- [Interpreting the Latent Space of GANs for Semantic Face Editing](https://mlsanity.com/paper/1907.10786/) (2019)
- [Explaining Machine Learning Classifiers through Diverse Counterfactual Explanations](https://mlsanity.com/paper/1905.07697/) (2019)
- [Closed-Form Factorization of Latent Semantics in GANs](https://mlsanity.com/paper/2007.06600/) (2020)
- [InterFaceGAN: Interpreting the Disentangled Face Representation Learned by GANs](https://mlsanity.com/paper/2005.09635/) (2020)
- [StyleSpace Analysis: Disentangled Controls for StyleGAN Image Generation](https://mlsanity.com/paper/2011.12799/) (2020)
- [Counterfactual Visual Explanations](https://mlsanity.com/paper/1904.07451/) (2019)
- [Simple Black-box Adversarial Attacks](https://mlsanity.com/paper/1905.07121/) (2019)
- [On Completeness-aware Concept-Based Explanations in Deep Neural Networks](https://mlsanity.com/paper/1910.07969/) (2019)
- [GANalyze: Toward Visual Definitions of Cognitive Image Properties](https://mlsanity.com/paper/1906.10112/) (2019)
- [Editing in Style: Uncovering the Local Semantics of GANs](https://mlsanity.com/paper/2004.14367/) (2020)
- [An open access repository of images on plant health to enable the development of mobile disease diagnostics](https://mlsanity.com/paper/1511.08060/) (2015)
- [Explaining Classifiers with Causal Concept Effect (CaCE)](https://mlsanity.com/paper/1907.07165/) (2019)
- [Getting a CLUE: A Method for Explaining Uncertainty Estimates](https://mlsanity.com/paper/2006.06848/) (2020)
- [Generative Hierarchical Features from Synthesizing Images](https://mlsanity.com/paper/2007.10379/) (2020)
- [Explanation by Progressive Exaggeration](https://mlsanity.com/paper/1911.00483/) (2019)
- [How Important Is a Neuron?](https://mlsanity.com/paper/1805.12233/) (2018)
- [Attribution in Scale and Space](https://mlsanity.com/paper/2004.03383/) (2020)
- [There and Back Again: Revisiting Backpropagation Saliency Methods](https://mlsanity.com/paper/2004.02866/) (2020)
- [A Disentangling Invertible Interpretation Network for Explaining Latent Representations](https://mlsanity.com/paper/2004.13166/) (2020)
- [Grader variability and the importance of reference standards for evaluating machine learning models for diabetic retinopathy](https://mlsanity.com/paper/1710.01711/) (2017)

## Built on by (most cited first, 30 of 122)

- [Imagic: Text-Based Real Image Editing with Diffusion Models](https://mlsanity.com/paper/2210.09276/) (2022)
- [Post-hoc Concept Bottleneck Models](https://mlsanity.com/paper/2205.15480/) (2022)
- [Interpreting CLIP's Image Representation via Text-Based Decomposition](https://mlsanity.com/paper/2310.05916/) (2023)
- [Diffusion Visual Counterfactual Explanations](https://mlsanity.com/paper/2210.11841/) (2022)
- [A Whac-A-Mole Dilemma: Shortcuts Come in Multiples Where Mitigating One Amplifies Others](https://mlsanity.com/paper/2212.04825/) (2022)
- [Discover and Cure: Concept-aware Mitigation of Spurious Correlation](https://mlsanity.com/paper/2305.00650/) (2023)
- [Discover and Mitigate Unknown Biases with Debiasing Alternate Networks](https://mlsanity.com/paper/2207.10077/) (2022)
- [Rosetta Neurons: Mining the Common Units in a Model Zoo](https://mlsanity.com/paper/2306.09346/) (2023)
- [Fast Diffusion-Based Counterfactuals for Shortcut Removal and Generation](https://mlsanity.com/paper/2312.14223/) (2023)
- [STEEX: Steering Counterfactual Explanations with Semantics](https://mlsanity.com/paper/2111.09094/) (2021)
- [Self-Distilled StyleGAN: Towards Generation from Internet Photos](https://mlsanity.com/paper/2202.12211/) (2022)
- [State-of-the-Art in the Architecture, Methods and Applications of StyleGAN](https://mlsanity.com/paper/2202.14020/) (2022)
- [StyleT2I: Toward Compositional and High-Fidelity Text-to-Image Synthesis](https://mlsanity.com/paper/2203.15799/) (2022)
- [Making Heads or Tails: Towards Semantically Consistent Visual Counterfactuals](https://mlsanity.com/paper/2203.12892/) (2022)
- [Sparse Visual Counterfactual Explanations in Image Space](https://mlsanity.com/paper/2205.07972/) (2022)
- [Evidence for Hypodescent in Visual Semantic AI](https://mlsanity.com/paper/2205.10764/) (2022)
- [Diffeomorphic Counterfactuals with Generative Models](https://mlsanity.com/paper/2206.05075/) (2022)
- [OCTET: Object-aware Counterfactual Explanations](https://mlsanity.com/paper/2211.12380/) (2022)
- [CheXplaining in Style: Counterfactual Explanations for Chest X-rays using StyleGAN](https://mlsanity.com/paper/2207.07553/) (2022)
- [We Can't Understand AI Using our Existing Vocabulary](https://mlsanity.com/paper/2502.07586/) (2025)
- [Zero-shot Model Diagnosis](https://mlsanity.com/paper/2303.15441/) (2023)
- [Region-Based Semantic Factorization in GANs](https://mlsanity.com/paper/2202.09649/) (2022)
- [Mitigating Dataset Bias by Using Per-sample Gradient](https://mlsanity.com/paper/2205.15704/) (2022)
- [WBCAtt: A White Blood Cell Dataset Annotated with Detailed Morphological Attributes](https://mlsanity.com/paper/2306.13531/) (2023)
- [FairStyle: Debiasing StyleGAN2 with Style Channel Manipulations](https://mlsanity.com/paper/2202.06240/) (2022)
- [Arbitrary-Scale Image Synthesis](https://mlsanity.com/paper/2204.02273/) (2022)
- [Latent Space Smoothing for Individually Fair Representations](https://mlsanity.com/paper/2111.13650/) (2021)
- [MICA: Towards Explainable Skin Lesion Diagnosis via Multi-Level Image-Concept Alignment](https://mlsanity.com/paper/2401.08527/) (2024)
- [LARGE: Latent-Based Regression through GAN Semantics](https://mlsanity.com/paper/2107.11186/) (2021)
- [GANterfactual-RL: Understanding Reinforcement Learning Agents' Strategies through Visual Counterfactual Explanations](https://mlsanity.com/paper/2302.12689/) (2023)

## Abstract (arXiv)

Image classification models can depend on multiple different semantic attributes of the image. An explanation of the decision of the classifier needs to both discover and visualize these properties. Here we present StylEx, a method for doing this, by training a generative model to specifically explain multiple attributes that underlie classifier decisions. A natural source for such attributes is the StyleSpace of StyleGAN, which is known to generate semantically meaningful dimensions in the image. However, because standard GAN training is not dependent on the classifier, it may not represent these attributes which are important for the classifier decision, and the dimensions of StyleSpace may represent irrelevant attributes. To overcome this, we propose a training procedure for a StyleGAN, which incorporates the classifier model, in order to learn a classifier-specific StyleSpace. Explanatory attributes are then selected from this space. These can be used to visualize the effect of changing multiple attributes per image, thus providing image-specific explanations. We apply StylEx to multiple domains, including animals, leaves, faces and retinal images. For these, we show how an image can be modified in different ways to change its classifier output. Our results show that the method finds attributes that align well with semantic ones, generate meaningful image-specific explanations, and are human-interpretable as measured in user-studies.