Class Balancing GAN with a Classifier in the Loop
This addresses the issue of GANs performing poorly on long-tailed datasets, which is a domain-specific problem for machine learning practitioners working with imbalanced data.
The paper tackles the problem of training Generative Adversarial Networks (GANs) on imbalanced datasets, where existing methods fail, by introducing a Class Balancing regularizer that uses a pre-trained classifier to ensure balanced learning across classes, resulting in improved performance such as reducing FID from 13.03 to 9.01 on the iNaturalist-2019 dataset.
Generative Adversarial Networks (GANs) have swiftly evolved to imitate increasingly complex image distributions. However, majority of the developments focus on performance of GANs on balanced datasets. We find that the existing GANs and their training regimes which work well on balanced datasets fail to be effective in case of imbalanced (i.e. long-tailed) datasets. In this work we introduce a novel theoretically motivated Class Balancing regularizer for training GANs. Our regularizer makes use of the knowledge from a pre-trained classifier to ensure balanced learning of all the classes in the dataset. This is achieved via modelling the effective class frequency based on the exponential forgetting observed in neural networks and encouraging the GAN to focus on underrepresented classes. We demonstrate the utility of our regularizer in learning representations for long-tailed distributions via achieving better performance than existing approaches over multiple datasets. Specifically, when applied to an unconditional GAN, it improves the FID from $13.03$ to $9.01$ on the long-tailed iNaturalist-$2019$ dataset.