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 …

With the emergence of machine learning methods, data-driven fault diagnosis has gained
significant attention in recent years. However, traditional data-driven diagnosis approaches …

As artificial intelligence (AI) rapidly approaches human-level performance in medical
imaging, it is crucial that it does not exacerbate or propagate healthcare disparities. Previous …

Abstract Machine-learning models for medical tasks can match or surpass the performance
of clinical experts. However, in settings differing from those of the training dataset, the …

Neural network classifiers can largely rely on simple spurious features, such as
backgrounds, to make predictions. However, even in these cases, we show that they still …

An estimated 3 billion people lack access to dermatological care globally. Artificial
intelligence (AI) may aid in triaging skin diseases and identifying malignancies. However …

Traditional machine learning paradigms are based on the assumption that both training and
test data follow the same statistical pattern, which is mathematically referred to as …

Abstract Federated Domain Generalization (FedDG) attempts to learn a global model in a
privacy-preserving manner that generalizes well to new clients possibly with domain shift …

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

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 …