Semantic image segmentation (SiS) plays a fundamental role in a broad variety of computer
vision applications, providing key information for the global understanding of an image. This …

Semantic segmentation plays a fundamental role in a broad variety of computer vision
applications, providing key information for the global understanding of an image. Yet, the …

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 …

Unsupervised domain adaptation in semantic segmentation alleviates the reliance on
expensive pixel-wise annotation. It uses a labeled source domain dataset as well as …

Recent advances in unsupervised domain adaptation (UDA) techniques have witnessed
great success in cross-domain computer vision tasks, enhancing the generalization ability of …

State-of-the-art methods for counting people in crowded scenes rely on deep networks to
estimate crowd density. While effective, these data-driven approaches rely on large amount …

Current domain adaptation methods for face anti-spoofing leverage labeled source domain
data and unlabeled target domain data to obtain a promising generalizable decision …

Measuring similarities between different tasks is critical in a broad spectrum of machine
learning problems, including transfer, multi-task, continual, and meta-learning. Most current …

Generalizable person Re-Identification (ReID) aims to learn ready-to-use cross-domain
representations for direct cross-data evaluation, which has attracted growing attention in the …

Abstract Domain adaptation aims to mitigate distribution shifts among different domains.
However, traditional formulations are mostly limited to categorical domains, greatly …