2 papers
cs.CV2026
Discrepancy Minimization Improves Cross-Hospital Robustness in Digital Pathology
Ben Vardi, Dana Schonberger, Yuval Friedmann +4
Pathology foundation models (PFMs) have advanced rapidly in recent years and support training classifiers for a range of histopathology tasks. However, their robustness across hosp…
cs.CV2023
Test-time augmentation-based active learning and self-training for label-efficient segmentation
Bella Specktor-Fadida, Anna Levchakov, Dana Schonberger +3
Deep learning techniques depend on large datasets whose annotation is time-consuming. To reduce annotation burden, the self-training (ST) and active-learning (AL) methods have been…