Domain generalization: A survey
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 …
challenging for machines to reproduce. This is because most learning algorithms strongly …
A brief review of domain adaptation
Classical machine learning assumes that the training and test sets come from the same
distributions. Therefore, a model learned from the labeled training data is expected to …
distributions. Therefore, a model learned from the labeled training data is expected to …
Towards out-of-distribution generalization: A survey
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 …
test data follow the same statistical pattern, which is mathematically referred to as …
Robust and data-efficient generalization of self-supervised machine learning for diagnostic imaging
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 …
of clinical experts. However, in settings differing from those of the training dataset, the …
Generalizing to unseen domains: A survey on domain generalization
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 …
the same. To this end, a key requirement is to develop models that can generalize to unseen …
A fourier-based framework for domain generalization
Modern deep neural networks suffer from performance degradation when evaluated on
testing data under different distributions from training data. Domain generalization aims at …
testing data under different distributions from training data. Domain generalization aims at …
Exact feature distribution matching for arbitrary style transfer and domain generalization
Arbitrary style transfer (AST) and domain generalization (DG) are important yet challenging
visual learning tasks, which can be cast as a feature distribution matching problem. With the …
visual learning tasks, which can be cast as a feature distribution matching problem. With the …
Feddg: Federated domain generalization on medical image segmentation via episodic learning in continuous frequency space
Federated learning allows distributed medical institutions to collaboratively learn a shared
prediction model with privacy protection. While at clinical deployment, the models trained in …
prediction model with privacy protection. While at clinical deployment, the models trained in …
Causality inspired representation learning for domain generalization
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 …
generalize the knowledge learned from multiple source domains to an unseen target …
Learning to diversify for single domain generalization
Abstract Domain generalization (DG) aims to generalize a model trained on multiple source
(ie, training) domains to a distributionally different target (ie, test) domain. In contrast to the …
(ie, training) domains to a distributionally different target (ie, test) domain. In contrast to the …