Inclusive GAN: Improving Data and Minority Coverage in Generative Models

2020/04/07 by Ning Yu, Yu, Ning, Ke Li +10 · 1 citation
Computer Science · #Advanced Image Processing Techniques #Advanced Vision and Imaging #Computer Vision and Pattern Recognition (cs.CV) #FOS: Computer and information sciences #Generative Adversarial Networks and Image Synthesis #cs.CV

paper · pdf · doi:10.48550/arxiv.2004.03355

Accepted to ECCV'20

openalex publication_date 2020/04/07 · arxiv created 2020/08/23 · arxiv updated 2020/08/25 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28

Abstract

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.

Citations

• LSUN: Construction of a Large-scale Image Dataset using Deep Learning with Humans in the Loop
• Auto-Encoding Variational Bayes
• Certifying and Removing Disparate Impact
• Fairness through awareness
• Gradient-based learning applied to document recognition
• Energy-based Generative Adversarial Network
• Equality of Opportunity in Supervised Learning
• Unrolled Generative Adversarial Networks
• BEGAN: Boundary Equilibrium Generative Adversarial Networks
• Variational Approaches for Auto-Encoding Generative Adversarial Networks
• Assessing Generative Models via Precision and Recall
• InclusiveFaceNet: Improving Face Attribute Detection with Race and Gender Diversity
• Implicit Maximum Likelihood Estimation
• Large Scale GAN Training for High Fidelity Natural Image Synthesis
• InfoGAN: Interpretable Representation Learning by Information Maximizing Generative Adversarial Nets
• Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networks
• A Survey on Bias and Fairness in Machine Learning
• On Adversarial Mixup Resynthesis
• "Best-of-Many-Samples" Distribution Matching
• Fair Generative Modeling via Weak Supervision

Cited by

• Score-based Idempotent Distillation of Diffusion Models

Related

• Fair GANs through model rebalancing for extremely imbalanced class distributions
• GAN You Do the GAN GAN?
• Multi-Agent Diverse Generative Adversarial Networks
• Self-Diagnosing GAN: Diagnosing Underrepresented Samples in Generative Adversarial Networks
• Generative Adversarial Networks with Limited Data: A Survey and Benchmarking