Image classification with small datasets has been an active research area in the recent past.
However, as research in this scope is still in its infancy, two key ingredients are missing for …

Solving image classification tasks given small training datasets remains an open challenge
for modern computer vision. Aggressive data augmentation and generative models are …

Numerical experiments demonstrate that deep neural network classifiers progressively
separate class distributions around their mean, achieving linear separability on the training …

Data-efficient image classification using deep neural networks in settings, where only small
amounts of labeled data are available, has been an active research area in the recent past …

Convolutional neural networks (CNNs) learn filters in order to capture local correlation
patterns in feature space. We propose to learn these filters as combinations of preset …

Convolutional neural networks have demonstrated impressive results in many computer
vision tasks. However, the increasing size of these networks raises concerns about the …

Spectral representations have been introduced into deep convolutional neural networks
(CNNs) mainly for accelerating convolutions and mitigating information loss. However …

In this paper, we aim to improve the mathematical interpretability of convolutional neural
networks for image classification. When trained on natural image datasets, such networks …

This paper investigates data synthesis with a Generative Adversarial Network (GAN) for
augmenting the amount of data used for training classifiers (in supervised learning) to …

Assessing asthma severity is inherently difficult because it is highly subjective, often
overlapping with symptoms of a common cold, and few objective tools currently exist for it …