Inclusive GAN: Improving Data and Minority Coverage in Generative Models
arXiv:2004.03355
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.
Accepted to ECCV'20
References in corpus (23)
- Auto-Encoding Variational Bayes
- GANs Trained by a Two Time-Scale Update Rule Converge to a Local Nash Equilibrium
- Large Scale GAN Training for High Fidelity Natural Image Synthesis
- Spectral Normalization for Generative Adversarial Networks
- Equality of Opportunity in Supervised Learning
- LSUN: Construction of a Large-scale Image Dataset using Deep Learning with Humans in the Loop
- Energy-based Generative Adversarial Network
- BEGAN: Boundary Equilibrium Generative Adversarial Networks
- VEEGAN: Reducing Mode Collapse in GANs using Implicit Variational Learning
- Unrolled Generative Adversarial Networks
- Variational Approaches for Auto-Encoding Generative Adversarial Networks
- Assessing Generative Models via Precision and Recall
- Variational Discriminator Bottleneck: Improving Imitation Learning, Inverse RL, and GANs by Constraining Information Flow
- Diversity-Sensitive Conditional Generative Adversarial Networks
- Banach Wasserstein GAN
- InclusiveFaceNet: Improving Face Attribute Detection with Race and Gender Diversity
- Bias and Generalization in Deep Generative Models: An Empirical Study
- Bias Correction of Learned Generative Models using Likelihood-Free Importance Weighting
- Implicit Maximum Likelihood Estimation
- On Adversarial Mixup Resynthesis
- Fast k-Nearest Neighbour Search via Prioritized DCI
- Fair Generative Modeling via Weak Supervision
- "Best-of-Many-Samples" Distribution Matching