Unsupervised Domain Adaptation by Uncertain Feature Alignment
This work addresses the problem of adapting models from labeled source to unlabeled target domains for machine learning practitioners, representing an incremental improvement.
The paper tackles unsupervised domain adaptation by using model prediction uncertainty, measured via Monte-Carlo dropout, to filter and align features, achieving state-of-the-art results on multiple challenging datasets.
Unsupervised domain adaptation (UDA) deals with the adaptation of models from a given source domain with labeled data to an unlabeled target domain. In this paper, we utilize the inherent prediction uncertainty of a model to accomplish the domain adaptation task. The uncertainty is measured by Monte-Carlo dropout and used for our proposed Uncertainty-based Filtering and Feature Alignment (UFAL) that combines an Uncertain Feature Loss (UFL) function and an Uncertainty-Based Filtering (UBF) approach for alignment of features in Euclidean space. Our method surpasses recently proposed architectures and achieves state-of-the-art results on multiple challenging datasets. Code is available on the project website.