Domain Confusion with Self Ensembling for Unsupervised Adaptation

Understand

Data collection and annotation are time-consuming in machine learning, expecially for large scale problem.

• A common approach for this problem is to transfer knowledge from a related labeled domain to a target one.
• There are two popular ways to achieve this goal: adversarial learning and self training.
• In this article, we first analyze the training unstablity problem and the mistaken confusion issue in adversarial learning process.