Data Augmentation in High Dimensional Low Sample Size Setting Using a Geometry-Based Variational Autoencoder - Archive ouverte HAL Accéder directement au contenu
Article Dans Une Revue IEEE Transactions on Pattern Analysis and Machine Intelligence Année : 2022

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

Résumé

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.
Fichier principal
Vignette du fichier
Data_Augmentation_HDLSS_VAE.pdf (6.12 Mo) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)

Dates et versions

hal-03214093 , version 1 (30-04-2021)

Identifiants

Citer

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, ⟨10.1109/TPAMI.2022.3185773⟩. ⟨hal-03214093⟩
324 Consultations
125 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More