EPL: Evidential Prototype Learning for Semi-supervised Medical Image Segmentation

arXiv:2404.06181v1 Announce Type: new
Abstract: Although current semi-supervised medical segmentation methods can achieve decent performance, they are still affected by the uncertainty in unlabeled data and model predictions, and there is currently a lack of effective strategies that can explore the uncertain aspects of both simultaneously. To address the aforementioned issues, we propose Evidential Prototype Learning (EPL), which utilizes an extended probabilistic framework to effectively fuse voxel probability predictions from different sources and achieves prototype fusion utilization of labeled and …

abstract arxiv cs.ai cs.cv current data explore image medical performance predictions segmentation semi-supervised strategies type uncertain uncertainty