We study how robust current ImageNet models are to distribution shifts arising from natural
variations in datasets. Most research on robustness focuses on synthetic image …

Overfitting describes the phenomenon where a highly predictive model on the training data
generalizes poorly to future observations. It is a common concern when applying machine …

We extend semi-supervised learning to the problem of domain adaptation to learn
significantly higher-accuracy models that train on one data distribution and test on a different …

Adversarial training augments the training set with perturbations to improve the robust error
(over worst-case perturbations), but it often leads to an increase in the standard error (on …

Deep neural networks (DNN) have been shown to be notoriously brittle to small
perturbations in their input data. This problem is analogous to the over-fitting problem in test …

Visual recognition models are not invariant to viewpoint changes in the 3D world, as
different viewing directions can dramatically affect the predictions given the same object …

Driven by massive amounts of data and important advances in computational resources,
new deep learning systems have achieved outstanding results in a large spectrum of …

In this paper, we cast fair machine learning as invariant machine learning. We first formulate
a version of individual fairness that enforces invariance on certain sensitive sets. We then …

Viewpoint invariance remains challenging for visual recognition in the 3D world, as altering
the viewing directions can significantly impact predictions for the same object. While …

Data augmentation (DA) is a powerful workhorse for bolstering performance in modern
machine learning. Specific augmentations like translations and scaling in computer vision …