Domain Confusion with Self Ensembling for Unsupervised Adaptation
This work addresses the challenge of transferring knowledge from labeled to unlabeled domains in machine learning, which is crucial for reducing data annotation efforts, but it appears incremental as it combines existing techniques.
The paper tackled the problem of training instability and mistaken confusion in adversarial learning for unsupervised domain adaptation by proposing a combined model called Domain Confusion with Self Ensembling (DCSE), which achieved better performance than state-of-the-art methods on various benchmarks.
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. Then, inspired by domain confusion and self-ensembling methods, we propose a combined model to learn feature and class jointly invariant representation, namely Domain Confusion with Self Ensembling (DCSE). The experiments verified that our proposed approach can offer better performance than empirical art in a variety of unsupervised domain adaptation benchmarks.