Think Twice Before Selection: Federated Evidential Active Learning for Medical Image Analysis with Domain Shifts

arXiv:2312.02567v2 Announce Type: replace
Abstract: Federated learning facilitates the collaborative learning of a global model across multiple distributed medical institutions without centralizing data. Nevertheless, the expensive cost of annotation on local clients remains an obstacle to effectively utilizing local data. To mitigate this issue, federated active learning methods suggest leveraging local and global model predictions to select a relatively small amount of informative local data for annotation. However, existing methods mainly focus on all local data sampled from the same …

active learning analysis arxiv cs.cv domain image medical think type