J. Paetzold

End-to-end meta-learning of neural field representations reveals that first-order approximations discard crucial learning pathways, leading to improved few-shot adaptation and semantic prediction.

RegAL outperforms traditional methods by effectively integrating active and semi-supervised learning, achieving robust segmentation with minimal labeled data.

Overconfident predictions in medical imaging segmentation can be corrected with a simple gradient adjustment that enhances model calibration without sacrificing accuracy.