Active Domain Adaptation via Clustering Uncertainty-weighted Embeddings
This addresses the cost-effective generalization of deep neural networks to new domains, though it is incremental as it builds on active learning and domain adaptation.
The paper tackles the problem of selecting informative target data for labeling in domain adaptation to reduce costs, proposing CLUE, which outperforms existing methods on 6 domain shifts for image classification.
Generalizing deep neural networks to new target domains is critical to their real-world utility. In practice, it may be feasible to get some target data labeled, but to be cost-effective it is desirable to select a maximally-informative subset via active learning (AL). We study the problem of AL under a domain shift, called Active Domain Adaptation (Active DA). We demonstrate how existing AL approaches based solely on model uncertainty or diversity sampling are less effective for Active DA. We propose Clustering Uncertainty-weighted Embeddings (CLUE), a novel label acquisition strategy for Active DA that performs uncertainty-weighted clustering to identify target instances for labeling that are both uncertain under the model and diverse in feature space. CLUE consistently outperforms competing label acquisition strategies for Active DA and AL across learning settings on 6 diverse domain shifts for image classification.