Class Balancing GAN with a Classifier in the Loop

Harsh Rangwani, Konda Reddy Mopuri, Venkatesh Babu Radhakrishnan

Keywords: Long-tailed Learning, GAN, Universal Adversarial Perturbations

Abstract: 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 and 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 contribution in two diverse scenarios: (i) Learning representations for long-tailed distributions, where we achieve better performance than existing approaches, and (ii) Generation of Universal Adversarial Perturbations (UAPs) in the data-free scenario for the large scale datasets, where we bridge the gap between data-driven and data-free approaches for crafting UAPs.

One-sentence Summary: A regularizer for balancing class distributions of GAN samples with application to long-tailed learning and data-free adversarial attacks.

Code Of Ethics: I acknowledge that I and all co-authors of this work have read and commit to adhering to the ICLR Code of Ethics

Community Implementations: [ 3 code implementations](https://www.catalyzex.com/paper/arxiv:2106.09402/code)

Reviewed Version (pdf): https://openreview.net/references/pdf?id=_lOTbDRIS9