Skip to Main content Skip to Navigation
New interface
Journal articles

Data Augmentation in High Dimensional Low Sample Size Setting Using a Geometry-Based Variational Autoencoder

Abstract : In this paper, we propose a new method to perform data augmentation in a reliable way in the High Dimensional Low Sample Size (HDLSS) setting using a geometry-based variational autoencoder. Our approach combines a proper latent space modeling of the VAE seen as a Riemannian manifold with a new generation scheme which produces more meaningful samples especially in the context of small data sets. The proposed method is tested through a wide experimental study where its robustness to data sets, classifiers and training samples size is stressed. It is also validated on a medical imaging classification task on the challenging ADNI database where a small number of 3D brain MRIs are considered and augmented using the proposed VAE framework. In each case, the proposed method allows for a significant and reliable gain in the classification metrics. For instance, balanced accuracy jumps from 66.3% to 74.3% for a state-of-the-art CNN classifier trained with 50 MRIs of cognitively normal (CN) and 50 Alzheimer disease (AD) patients and from 77.7% to 86.3% when trained with 243 CN and 210 AD while improving greatly sensitivity and specificity metrics.
Document type :
Journal articles
Complete list of metadata
Contributor : Clément Chadebec Connect in order to contact the contributor
Submitted on : Friday, April 30, 2021 - 6:43:15 PM
Last modification on : Wednesday, October 26, 2022 - 2:08:40 PM
Long-term archiving on: : Saturday, July 31, 2021 - 7:29:50 PM


Files produced by the author(s)


  • HAL Id : hal-03214093, version 1


Clément Chadebec, Elina Thibeau-Sutre, Ninon Burgos, Stéphanie Allassonnière. Data Augmentation in High Dimensional Low Sample Size Setting Using a Geometry-Based Variational Autoencoder. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2022. ⟨hal-03214093⟩



Record views


Files downloads