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 …

Abstract Domain generalization person re-identification (DG ReID) aims to train a model on
source domains and generalize well on unseen domains. Vision Transformer usually yields …

Abstract Domain generalization studies the problem of training a model with samples from
several domains (or distributions) and then testing the model with samples from a new …

Unsupervised domain adaptation (UDA) involves a supervised loss in a labeled source
domain and an unsupervised loss in an unlabeled target domain, which often faces more …

Medical Image Analysis (MedIA) has become an essential tool in medicine and healthcare,
aiding in disease diagnosis, prognosis, and treatment planning, and recent successes in …

Existing video-audio understanding models are trained and evaluated in an intra-domain
setting, facing performance degeneration in real-world applications where multiple domains …

Medical image analysis (MedIA) has become an essential tool in medicine and healthcare,
aiding in disease diagnosis, prognosis, and treatment planning, and recent successes in …

Abstract Domain adaptive semantic segmentation methods commonly utilize stage-wise
training, consisting of a warm-up and a self-training stage. However, this popular approach …

Abstract Domain generalization (DG) attempts to learn a model on source domains that can
well generalize to unseen but different domains. The multiple source domains are innately …

In the recent past, several domain generalization (DG) methods have been proposed,
showing encouraging performance, however, almost all of them build on convolutional …