Deep Active Learning for Robust Biomedical Segmentation
M. Arikan, F. Sallo, A. Montesel, H. Ahmed, A. Hagag, M. Book, H. Faatz, M. Cicinelli, S. Meshkinfamfard, S. Ongun, A. Dubis, W. Lilaonitkul
This paper introduces a deep active learning framework that reduces annotation needs by 39-54% while improving robustness in medical image segmentation.
bioRxiv · Mar 28, 2023 · PreprintBioengineering