We demonstrate that differentially private machine learning has not yet reached its" AlexNet
moment" on many canonical vision tasks: linear models trained on handcrafted features …

In this paper we challenge the common assumption that convolutional layers in modern
CNNs are translation invariant. We show that CNNs can and will exploit the absolute spatial …

Explanations of a model's biases or predictions are essential to medical image analysis. Yet,
explainable machine learning approaches for medical image analysis are challenged by …

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 …

Shallow supervised 1-hidden layer neural networks have a number of favorable properties
that make them easier to interpret, analyze, and optimize than their deep counterparts, but …

The wavelet scattering transform is an invariant and stable signal representation suitable for
many signal processing and machine learning applications. We present the Kymatio …

Medical image classification plays an important role in disease diagnosis since it can
provide important reference information for doctors. The supervised convolutional neural …

Over the past year, the AI community has constructed several deep learning models for
diagnosing COVID-19 based on the visual features of chest X-rays. While deep learning …

Deep convolutional neural networks (DCNNs) have recently emerged as a powerful tool to
deliver breakthrough performances in various image analysis and processing applications …

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