# Inclusive GAN: Improving Data and Minority Coverage in Generative Models

arXiv: https://arxiv.org/abs/2004.03355 · HTML: https://mlsanity.com/paper/2004.03355/

## Key facts

- Cited by 44 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 7 Apr 2020.

## Built on by (most cited first, 30 of 44)

- [Tackling the Generative Learning Trilemma with Denoising Diffusion GANs](https://mlsanity.com/paper/2112.07804/) (2021)
- [EditGAN: High-Precision Semantic Image Editing](https://mlsanity.com/paper/2111.03186/) (2021)
- [Pros and Cons of GAN Evaluation Measures: New Developments](https://mlsanity.com/paper/2103.09396/) (2021)
- [Ensembling Off-the-shelf Models for GAN Training](https://mlsanity.com/paper/2112.09130/) (2021)
- [ITI-GEN: Inclusive Text-to-Image Generation](https://mlsanity.com/paper/2309.05569/) (2023)
- [Don't Generate Me: Training Differentially Private Generative Models with Sinkhorn Divergence](https://mlsanity.com/paper/2111.01177/) (2021)
- [Balancing Act: Distribution-Guided Debiasing in Diffusion Models](https://mlsanity.com/paper/2402.18206/) (2024)
- [Analyzing Bias in Diffusion-based Face Generation Models](https://mlsanity.com/paper/2305.06402/) (2023)
- [Beyond the Spectrum: Detecting Deepfakes via Re-Synthesis](https://mlsanity.com/paper/2105.14376/) (2021)
- [Self-Distilled StyleGAN: Towards Generation from Internet Photos](https://mlsanity.com/paper/2202.12211/) (2022)
- [Don't Play Favorites: Minority Guidance for Diffusion Models](https://mlsanity.com/paper/2301.12334/) (2023)
- [Using StyleGAN for Visual Interpretability of Deep Learning Models on Medical Images](https://mlsanity.com/paper/2101.07563/) (2021)
- [Fairness for Image Generation with Uncertain Sensitive Attributes](https://mlsanity.com/paper/2106.12182/) (2021)
- [Dual Contrastive Loss and Attention for GANs](https://mlsanity.com/paper/2103.16748/) (2021)
- [Copyright in Generative Deep Learning](https://mlsanity.com/paper/2105.09266/) (2021)
- [Improving Geo-diversity of Generated Images with Contextualized Vendi Score Guidance](https://mlsanity.com/paper/2406.04551/) (2024)
- [ID-Blau: Image Deblurring by Implicit Diffusion-based reBLurring AUgmentation](https://mlsanity.com/paper/2312.10998/) (2023)
- [Generalized One-shot Domain Adaptation of Generative Adversarial Networks](https://mlsanity.com/paper/2209.03665/) (2022)
- [Self-Guided Generation of Minority Samples Using Diffusion Models](https://mlsanity.com/paper/2407.11555/) (2024)
- [Minority-Focused Text-to-Image Generation via Prompt Optimization](https://mlsanity.com/paper/2410.07838/) (2024)
- [Boomerang: Local sampling on image manifolds using diffusion models](https://mlsanity.com/paper/2210.12100/) (2022)
- [LayoutDETR: Detection Transformer Is a Good Multimodal Layout Designer](https://mlsanity.com/paper/2212.09877/) (2022)
- [Improving GANs for Long-Tailed Data through Group Spectral Regularization](https://mlsanity.com/paper/2208.09932/) (2022)
- [Self-Diagnosing GAN: Diagnosing Underrepresented Samples in Generative Adversarial Networks](https://mlsanity.com/paper/2102.12033/) (2021)
- [Fairness and Bias Mitigation in Computer Vision: A Survey](https://mlsanity.com/paper/2408.02464/) (2024)
- [From Posterior Sampling to Meaningful Diversity in Image Restoration](https://mlsanity.com/paper/2310.16047/) (2023)
- [MCL-GAN: Generative Adversarial Networks with Multiple Specialized Discriminators](https://mlsanity.com/paper/2107.07260/) (2021)
- [Uncovering Bias in Face Generation Models](https://mlsanity.com/paper/2302.11562/) (2023)
- [On Measuring Fairness in Generative Models](https://mlsanity.com/paper/2310.19297/) (2023)
- [FairGen: Enhancing Fairness in Text-to-Image Diffusion Models via Self-Discovering Latent Directions](https://mlsanity.com/paper/2412.18810/) (2024)

## Abstract (arXiv)

Generative Adversarial Networks (GANs) have brought about rapid progress towards generating photorealistic images. Yet the equitable allocation of their modeling capacity among subgroups has received less attention, which could lead to potential biases against underrepresented minorities if left uncontrolled. In this work, we first formalize the problem of minority inclusion as one of data coverage, and then propose to improve data coverage by harmonizing adversarial training with reconstructive generation. The experiments show that our method outperforms the existing state-of-the-art methods in terms of data coverage on both seen and unseen data. We develop an extension that allows explicit control over the minority subgroups that the model should ensure to include, and validate its effectiveness at little compromise from the overall performance on the entire dataset. Code, models, and supplemental videos are available at GitHub.