Unsupervised Domain Adaptation by Uncertain Feature Alignment
arXiv:2009.06483
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 (8)
- Conditional Adversarial Domain Adaptation
- VisDA: The Visual Domain Adaptation Challenge
- Train longer, generalize better: closing the generalization gap in large batch training of neural networks
- Contrastive Adaptation Network for Unsupervised Domain Adaptation
- Domain-Symmetric Networks for Adversarial Domain Adaptation
- Drop to Adapt: Learning Discriminative Features for Unsupervised Domain Adaptation
- Unsupervised Domain Adaptation with Random Walks on Target Labelings
- Attending to Discriminative Certainty for Domain Adaptation