Unsupervised Domain Adaptation by Uncertain Feature Alignment

Abstract

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.

Accepted at the 31st British Machine Vision Virtual Conference (BMVC 2020)

References in corpus (4)

• VisDA: The Visual Domain Adaptation Challenge
• Contrastive Adaptation Network for Unsupervised Domain Adaptation
• Domain-Symmetric Networks for Adversarial Domain Adaptation
• Drop to Adapt: Learning Discriminative Features for Unsupervised Domain Adaptation