Pythae: Unifying Generative Autoencoders in Python -- A Benchmarking Use Case

TL;DR

Pythae is an open-source Python library that unifies various generative autoencoder models, enabling easy benchmarking and comparison across multiple tasks like image reconstruction, generation, and clustering.

Contribution

This paper introduces Pythae, a comprehensive library that standardizes implementation and benchmarking of diverse VAE models for reproducible research.

Findings

Comparison of 19 autoencoder models on multiple tasks

Identification of best models for specific applications

Demonstration of library's ease of use and versatility

Abstract

In recent years, deep generative models have attracted increasing interest due to their capacity to model complex distributions. Among those models, variational autoencoders have gained popularity as they have proven both to be computationally efficient and yield impressive results in multiple fields. Following this breakthrough, extensive research has been done in order to improve the original publication, resulting in a variety of different VAE models in response to different tasks. In this paper we present Pythae, a versatile open-source Python library providing both a unified implementation and a dedicated framework allowing straightforward, reproducible and reliable use of generative autoencoder models. We then propose to use this library to perform a case study benchmark where we present and compare 19 generative autoencoder models representative of some of the main improvements on downstream tasks such as image reconstruction, generation, classification, clustering and interpolation. The open-source library can be found at https://github.com/clementchadebec/benchmark_VAE.