Active Domain Adaptation via Clustering Uncertainty-weighted Embeddings

TL;DR

This paper introduces CLUE, a new active learning strategy for domain adaptation that combines uncertainty and diversity in clustering to select informative target samples, improving performance across various domain shifts.

Contribution

The paper proposes CLUE, a novel clustering-based active learning method that effectively balances uncertainty and diversity for domain adaptation tasks.

Findings

CLUE outperforms existing strategies in multiple domain shift scenarios.

It effectively identifies uncertain and diverse samples for labeling.

Results demonstrate improved accuracy in image classification under domain shifts.

Abstract

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.