Papers › Data Augmentation with Variational Autoencoders and Manifold Sampling

Data Augmentation with Variational Autoencoders and Manifold Sampling

25 Mar 2021arXiv:2103.13751archive 2025-07-28

Clément Chadebec, Stéphanie Allassonnière

We propose a new efficient way to sample from a Variational Autoencoder in the challenging low sample size setting. This method reveals particularly well suited to perform data augmentation in such a low data regime and is validated across various standard and real-life data sets. In particular, this scheme allows to greatly improve classification results on the OASIS database where balanced accuracy jumps from 80.7% for a classifier trained with the raw data to 88.6% when trained only with the synthetic data generated by our method. Such results were also observed on 3 standard data sets and with other classifiers. A code is available at https://github.com/clementchadebec/Data_Augmentation_with_VAE-DALI.

PaperPDFCode

Code

clementchadebec/data_augmentation_with_vae-dali officialmentioned in paperpytorch report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

Data Augmentation

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

OASIS

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections