BriefGPT.xyz
Mar, 2024
主动学习中的多样性和不确定性的桥接与自监督预训练
Bridging Diversity and Uncertainty in Active learning with Self-Supervised Pre-Training
HTML
PDF
Paul Doucet, Benjamin Estermann, Till Aczel, Roger Wattenhofer
TL;DR
使用 TCM 方法，将多样性采样和不确定性采样策略整合到主动学习中，解决了冷启动问题，在低数据和高数据情况下均表现出卓越的性能。
Abstract
This study addresses the integration of diversity-based and
uncertainty-based sampling
strategies in
active learning
, particularly within the context of
→