Generalization to out-of-distribution (OOD) data is a capability natural to humans yet
challenging for machines to reproduce. This is because most learning algorithms strongly …

Large-scale labeled training datasets have enabled deep neural networks to excel across a
wide range of benchmark vision tasks. However, in many applications, it is prohibitively …

Machine learning systems generally assume that the training and testing distributions are
the same. To this end, a key requirement is to develop models that can generalize to unseen …

Modern deep neural networks suffer from performance degradation when evaluated on
testing data under different distributions from training data. Domain generalization aims at …

Classic machine learning methods are built on the $ iid $ assumption that training and
testing data are independent and identically distributed. However, in real scenarios, the $ iid …

Federated learning allows distributed medical institutions to collaboratively learn a shared
prediction model with privacy protection. While at clinical deployment, the models trained in …

The goal of domain generalization algorithms is to predict well on distributions different from
those seen during training. While a myriad of domain generalization algorithms exist …

Though convolutional neural networks (CNNs) have demonstrated remarkable ability in
learning discriminative features, they often generalize poorly to unseen domains. Domain …

The field of meta-learning, or learning-to-learn, has seen a dramatic rise in interest in recent
years. Contrary to conventional approaches to AI where tasks are solved from scratch using …

This paper presents a new algorithm for domain generalization (DG),\textit {test-time
template adjuster (T3A)}, aiming to robustify a model to unknown distribution shift. Unlike …