Machine learning techniques used in computer-aided medical image analysis usually suffer
from the domain shift problem caused by different distributions between source/reference …

Meta-learning empowers learning systems with the ability to acquire knowledge from
multiple tasks, enabling faster adaptation and generalization to new tasks. This review …

Abstract Domain generalization (DG) methods aim to achieve generalizability to an unseen
target domain by using only training data from the source domains. Although a variety of DG …

Generative adversarial networks (GANs) have recently become a hot research topic;
however, they have been studied since 2014, and a large number of algorithms have been …

Transfer learning aims at improving the performance of target learners on target domains by
transferring the knowledge contained in different but related source domains. In this way, the …

Conventional domain adaptation (DA) techniques aim to improve domain transferability by
learning domain-invariant representations; while concurrently preserving the task …

The standard objective in machine learning is to train a single model for all users. However,
in many learning scenarios, such as cloud computing and federated learning, it is possible …

We study how neural networks trained by gradient descent extrapolate, ie, what they learn
outside the support of the training distribution. Previous works report mixed empirical results …

Despite their renowned in-domain predictive power, convolutional neural networks are
known to rely more on high-frequency patterns that humans deem superficial than on low …

Conventional unsupervised domain adaptation (UDA) assumes that training data are
sampled from a single domain. This neglects the more practical scenario where training data …