On Training Sample Memorization: Lessons from Benchmarking Generative Modeling with a Large-scale Competition
Journal
Proceedings of the ACM SIGKDD International Conference on Knowledge Discovery and Data Mining
Pages
2534-2542
Date Issued
2021
Author(s)
Abstract
Many recent developments on generative models for natural images have relied on heuristically-motivated metrics that can be easily gamed by memorizing a small sample from the true distribution or training a model directly to improve the metric. In this work, we critically evaluate the gameability of these metrics by designing and deploying a generative modeling competition. Our competition received over 11000 submitted models. The competitiveness between participants allowed us to investigate both intentional and unintentional memorization in generative modeling. To detect intentional memorization, we propose the "Memorization-Informed Frechet Inception Distance"(MiFID) as a new memorization-aware metric and design benchmark procedures to ensure that winning submissions made genuine improvements in perceptual quality. Furthermore, we manually inspect the code for the 1000 top-performing models to understand and label different forms of memorization. Our analysis reveals that unintentional memorization is a serious and common issue in popular generative models. The generated images and our memorization labels of those models as well as code to compute MiFID are released to facilitate future studies on benchmarking generative models. ? 2021 Owner/Author.
Subjects
benchmark
competition
computer vision
datasets
generative models
memorization
neural networks
Benchmarking
Image enhancement
Frechet
Generative model
Natural images
Perceptual quality
Small samples
Training sample
Data mining
Type
conference paper