A Flexible Measurement of Diversity in Datasets with Random Network Distillation

Abstract

Generative models are increasingly able to produce remarkably high quality images and text. The community has developed numerous evaluation metrics for comparing generative models. However, these metrics do not always effectively quantify data diversity. We develop a new, more flexible diversity metric that can readily be applied to data, both synthetic and natural, of any type. Our method employs random network distillation, a technique introduced in reinforcement learning. We validate and deploy this metric on both images and text. We further explore diversity in few-shot image generation, a setting which was previously difficult to evaluate.

Tasks

Reproductions