# Mimicry: Towards the Reproducibility of GAN Research

arXiv: https://arxiv.org/abs/2005.02494 · HTML: https://mlsanity.com/paper/2005.02494/

## Key facts

- Cited by 14 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 5 May 2020.

## Built on by (most cited first, 14 of 14)

- [Pros and Cons of GAN Evaluation Measures: New Developments](https://mlsanity.com/paper/2103.09396/) (2021)
- [StudioGAN: A Taxonomy and Benchmark of GANs for Image Synthesis](https://mlsanity.com/paper/2206.09479/) (2022)
- [Representing 3D Shapes with Probabilistic Directed Distance Fields](https://mlsanity.com/paper/2112.05300/) (2021)
- [Closed-Loop Data Transcription to an LDR via Minimaxing Rate Reduction](https://mlsanity.com/paper/2111.06636/) (2021)
- [medigan: a Python library of pretrained generative models for medical image synthesis](https://mlsanity.com/paper/2209.14472/) (2022)
- [Self-Diagnosing GAN: Diagnosing Underrepresented Samples in Generative Adversarial Networks](https://mlsanity.com/paper/2102.12033/) (2021)
- [Learning Probabilistic Models from Generator Latent Spaces with Hat EBM](https://mlsanity.com/paper/2210.16486/) (2022)
- [F-Drop&Match: GANs with a Dead Zone in the High-Frequency Domain](https://mlsanity.com/paper/2106.02343/) (2021)
- [GraN-GAN: Piecewise Gradient Normalization for Generative Adversarial Networks](https://mlsanity.com/paper/2111.03162/) (2021)
- [Investigating Shifts in GAN Output-Distributions](https://mlsanity.com/paper/2112.14061/) (2021)
- [EBM Life Cycle: MCMC Strategies for Synthesis, Defense, and Density Modeling](https://mlsanity.com/paper/2205.12243/) (2022)
- [Explicit Use of Fourier Spectrum in Generative Adversarial Networks](https://mlsanity.com/paper/2208.01265/) (2022)
- [Probabilistic Directed Distance Fields for Ray-Based Shape Representations](https://mlsanity.com/paper/2404.09081/) (2024)
- [ParaGAN: A Scalable Distributed Training Framework for Generative Adversarial Networks](https://mlsanity.com/paper/2411.03999/) (2024)

## Abstract (arXiv)

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.