论文标题
通过聚类不确定性加权嵌入的活动域适应
Active Domain Adaptation via Clustering Uncertainty-weighted Embeddings
论文作者
论文摘要
将深层神经网络概括为新的目标域对于其现实世界的实用程序至关重要。实际上，可以将一些目标数据标记为可行，但是要具有成本效益，希望通过主动学习（AL）选择最大信息的子集。我们研究了在域移位下AL的问题，称为活动域适应（Active DA）。我们证明了仅基于模型不确定性或多样性采样的现有AL方法对主动DA的有效性较低。我们提出了聚类不确定性加权嵌入（线索），这是一种新型的活跃DA的标签采集策略，可执行不确定性加权的聚类，以识别在该模型下既不确定又不确定的标签目标实例，并且在特征空间中均不确定。线索始终超过竞争的标签采集策略，用于主动DA和AL，跨越6种不同领域的学习设置，以进行图像分类。
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.
