Pythae: Unifying Generative Autoencoders in Python - A Benchmarking Use Case - Inria - Institut national de recherche en sciences et technologies du numérique Access content directly
Conference Papers Year : 2022

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

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.
Fichier principal
Vignette du fichier
pythae_benchmark.pdf (24.88 Mo) Télécharger le fichier
Origin Files produced by the author(s)

Dates and versions

hal-03697439 , version 1 (16-06-2022)

Identifiers

  • HAL Id : hal-03697439 , version 1

Cite

Clément Chadebec, Louis J Vincent, Stéphanie Allassonnière. Pythae: Unifying Generative Autoencoders in Python - A Benchmarking Use Case. Proceedings of the Neural Information Processing Systems Track on Datasets and Benchmark, Nov 2022, New Orleans, United States. ⟨hal-03697439⟩
185 View
62 Download

Share

Gmail Mastodon Facebook X LinkedIn More