Large-scale labeled training datasets have enabled deep neural networks to excel across a
wide range of benchmark vision tasks. However, in many applications, it is prohibitively …

Deep Neural Networks (DNNs) trained on one dataset (source domain) do not perform well
on another set of data (target domain), which is different but has similar properties as the …

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

In this work, we connect two distinct concepts for unsupervised domain adaptation: feature
distribution alignment between domains by utilizing the task-specific decision boundary and …

Recent work has shown that the accuracy of machine learning models can vary substantially
when evaluated on a distribution that even slightly differs from that of the training data. As a …

Unsupervised domain adaptation algorithms aim to transfer the knowledge learned from one
domain to another (eg, synthetic to real images). The adapted representations often do not …

Rendering synthetic data (eg, 3D CAD-rendered images) to generate annotations for
learning deep models in vision tasks has attracted increasing attention in recent years …

Given labeled instances on a source domain and unlabeled ones on a target domain,
unsupervised domain adaptation aims to learn a task classifier that can well classify target …

The aim of unsupervised domain adaptation is to leverage the knowledge in a labeled
(source) domain to improve a model's learning performance with an unlabeled (target) …

Although various image-based domain adaptation (DA) techniques have been proposed in
recent years, domain shift in videos is still not well-explored. Most previous works only …