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 …

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 …

Abstract Domain generalization (DG) is essentially an out-of-distribution problem, aiming to
generalize the knowledge learned from multiple source domains to an unseen target …

Approaches based on deep neural networks have achieved striking performance when
testing data and training data share similar distribution, but can significantly fail otherwise …

Though remarkable progress has been achieved in various vision tasks, deep neural
networks still suffer obvious performance degradation when tested in out-of-distribution …

Deep neural networks (DNNs) have revolutionized artificial intelligence but often lack
performance when faced with out-of-distribution data, a common scenario due to the …

Unsupervised domain adaptation (DA) has gained substantial interest in semantic
segmentation. However, almost all prior arts assume concurrent access to both labeled …

In the domain generalization literature, a common objective is to learn representations
independent of the domain after conditioning on the class label. We show that this objective …

Abstract Out-of-distribution (OOD) generalization, where the model needs to handle
distribution shifts from training, is a major challenge of machine learning. Contrastive …