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

  title={Data Augmentation in High Dimensional Low Sample Size Setting Using a Geometry-Based Variational Autoencoder},
  author={Cl'ement Chadebec and Elina Thibeau-Sutre and Ninon Burgos and St{\'e}phanie Allassonni{\`e}re},
  journal={IEEE transactions on pattern analysis and machine intelligence},
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 (VAE). Our approach combines the proposal of 1) a new VAE model, the latent space of which is modeled as a Riemannian manifold and which combines both Riemannian metric learning and normalizing flows and 2) a new generation scheme which produces more meaningful samples especially in the context of small data… 

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

Pythae is presented, 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.

Confidence-Guided Data Augmentation for Deep Semi-Supervised Training

The proposed scheme improves classification performance in terms of accuracy and robustness, while yielding comparable or superior results with respect to existing fully supervised ap-proaches.

A Geometric Perspective on Variational Autoencoders

A new proposed sampling method consists in sampling from the uniform distribution deriving intrinsically from the learned Riemannian latent space and it is shown that using this scheme can make a vanilla VAE competitive and even better than more advanced versions on several benchmark datasets.

XADLiME: eXplainable Alzheimer's Disease Likelihood Map Estimation via Clinically-guided Prototype Learning

This work proposes a novel deep-learning approach through eXplainable AD Likelihood Map Estimation (XADLiME) for AD progression modeling over 3D sMRIs using clinically-guided prototype learning and promotes the explainability of such a likelihood map by revealing a comprehensible overview from two perspectives: clinical and morphological.

An Information-Theoretic Perspective on Proper Quaternion Variational Autoencoders

This paper analyze the QVAE under an information-theoretic perspective, studying the ability of the H-proper model to approximate improper distributions as well as the built-in H- Proper ones and the loss of entropy due to the improperness of the input signal.



The mnist database of handwritten digits

An improved articulated bar flail having shearing edges for efficiently shredding materials and an improved shredder cylinder with a plurality of these flails circumferentially spaced and pivotally attached to the periphery of a rotatable shaft are disclosed.

VAE with a VampPrior

This paper proposes to extend the variational auto-encoder (VAE) framework with a new type of prior called "Variational Mixture of Posteriors" prior, or VampPrior for short, which consists of a mixture distribution with components given by variational posteriors conditioned on learnable pseudo-inputs.

From Variational to Deterministic Autoencoders

It is shown, in a rigorous empirical study, that the proposed regularized deterministic autoencoders are able to generate samples that are comparable to, or better than, those of VAEs and more powerful alternatives when applied to images as well as to structured data such as molecules.

Hamiltonian Variational Auto-Encoder

It is shown here how to optimally select reverse kernels in this setting and, by building upon Hamiltonian Importance Sampling (HIS), a scheme that provides low-variance unbiased estimators of the ELBO and its gradients using the reparameterization trick is obtained.

Automatic differentiation in PyTorch

An automatic differentiation module of PyTorch is described — a library designed to enable rapid research on machine learning models that focuses on differentiation of purely imperative programs, with a focus on extensibility and low overhead.

Metrics for Deep Generative Models

The method yields a principled distance measure, provides a tool for visual inspection of deep generative models, and an alternative to linear interpolation in latent space and can be applied for robot movement generalization using previously learned skills.

EMNIST: Extending MNIST to handwritten letters

A variant of the full NIST dataset is introduced, which is called Extended MNIST (EMNIST), which follows the same conversion paradigm used to create the MNIST dataset, and one that shares the same image structure and parameters as the original MNIST task, allowing for direct compatibility with all existing classifiers and systems.

Convolutional Neural Networks for Classification of Alzheimer's Disease: Overview and Reproducible Evaluation

Wasserstein GAN

The problem this paper is concerned with is that of unsupervised learning, what does it mean to learn a probability distribution and how to define a parametric family of densities.

Generative Adversarial Nets

We propose a new framework for estimating generative models via an adversarial process, in which we simultaneously train two models: a generative model G that captures the data distribution, and a