Mimicry: Towards the Reproducibility of GAN Research

Abstract

Advancing the state of Generative Adversarial Networks (GANs) research requires one to make careful and accurate comparisons with existing works. Yet, this is often difficult to achieve in practice when models are often implemented differently using varying frameworks, and evaluated using different procedures even when the same metric is used. To mitigate these issues, we introduce Mimicry, a lightweight PyTorch library that provides implementations of popular state-of-the-art GANs and evaluation metrics to closely reproduce reported scores in the literature. We provide comprehensive baseline performances of different GANs on seven widely-used datasets by training these GANs under the same conditions, and evaluating them across three popular GAN metrics using the same procedures. The library can be found at https://github.com/kwotsin/mimicry.

Accepted to the AI for Content Creation Workshop at CVPR 2020

References in corpus (2)

• GANs Trained by a Two Time-Scale Update Rule Converge to a Local Nash Equilibrium
• Few-shot Video-to-Video Synthesis

Cited by in corpus (9)

• medigan: a Python library of pretrained generative models for medical image synthesis
• Self-Diagnosing GAN: Diagnosing Underrepresented Samples in Generative Adversarial Networks
• SSD-GAN: Measuring the Realness in the Spatial and Spectral Domains
• GraN-GAN: Piecewise Gradient Normalization for Generative Adversarial Networks
• Slimmable Generative Adversarial Networks
• Neural Function Modules with Sparse Arguments: A Dynamic Approach to Integrating Information across Layers
• F-Drop&Match: GANs with a Dead Zone in the High-Frequency Domain
• Generative Model without Prior Distribution Matching
• Multiclass non-Adversarial Image Synthesis, with Application to Classification from Very Small Sample