# Multi-Attribute Balanced Sampling for Disentangled GAN Controls

arXiv: https://arxiv.org/abs/2111.00909 · HTML: https://mlsanity.com/paper/2111.00909/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Builds on 25 of its 27 references that are in the map.
- First posted on arXiv 28 Oct 2021.

## Builds on (most cited first, 25 of 25)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [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)
- [Progressive Growing of GANs for Improved Quality, Stability, and Variation](https://mlsanity.com/paper/1710.10196/) (2017)
- [Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networks](https://mlsanity.com/paper/1511.06434/) (2015)
- [Alias-Free Generative Adversarial Networks](https://mlsanity.com/paper/2106.12423/) (2021)
- [VGGFace2: A dataset for recognising faces across pose and age](https://mlsanity.com/paper/1710.08092/) (2017)
- [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)
- [InterFaceGAN: Interpreting the Disentangled Face Representation Learned by GANs](https://mlsanity.com/paper/2005.09635/) (2020)
- [StyleFlow: Attribute-conditioned Exploration of StyleGAN-Generated Images using Conditional Continuous Normalizing Flows](https://mlsanity.com/paper/2008.02401/) (2020)
- [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 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)
- [Bias and Generalization in Deep Generative Models: An Empirical Study](https://mlsanity.com/paper/1811.03259/) (2018)
- [Image Counterfactual Sensitivity Analysis for Detecting Unintended Bias](https://mlsanity.com/paper/1906.06439/) (2019)
- [Enjoy Your Editing: Controllable GANs for Image Editing via Latent Space Navigation](https://mlsanity.com/paper/2102.01187/) (2021)
- [GAN "Steerability" without optimization](https://mlsanity.com/paper/2012.05328/) (2020)
- [GuidedStyle: Attribute Knowledge Guided Style Manipulation for Semantic Face Editing](https://mlsanity.com/paper/2012.11856/) (2020)
- [Hijack-GAN: Unintended-Use of Pretrained, Black-Box GANs](https://mlsanity.com/paper/2011.14107/) (2020)

## Built on by (most cited first, 4 of 4)

- [Multi-Directional Subspace Editing in Style-Space](https://mlsanity.com/paper/2211.11825/) (2022)
- [Fairer Analysis and Demographically Balanced Face Generation for Fairer Face Verification](https://mlsanity.com/paper/2412.03349/) (2024)
- [Wasserstein Loss for Semantic Editing in the Latent Space of GANs](https://mlsanity.com/paper/2304.10508/) (2023)
- [Sampling Strategies for Mitigating Bias in Face Synthesis Methods](https://mlsanity.com/paper/2405.11320/) (2024)

## Abstract (arXiv)

Various controls over the generated data can be extracted from the latent space of a pre-trained GAN, as it implicitly encodes the semantics of the training data. The discovered controls allow to vary semantic attributes in the generated images but usually lead to entangled edits that affect multiple attributes at the same time. Supervised approaches typically sample and annotate a collection of latent codes, then train classifiers in the latent space to identify the controls. Since the data generated by GANs reflects the biases of the original dataset, so do the resulting semantic controls. We propose to address disentanglement by subsampling the generated data to remove over-represented co-occuring attributes thus balancing the semantics of the dataset before training the classifiers. We demonstrate the effectiveness of this approach by extracting disentangled linear directions for face manipulation on two popular GAN architectures, PGGAN and StyleGAN, and two datasets, CelebAHQ and FFHQ. We show that this approach outperforms state-of-the-art classifier-based methods while avoiding the need for disentanglement-enforcing post-processing.