BioengineeringIEEE International Symposium on Biomedical Imaging (ISBI)Peer-reviewed
CGMD: Centrality-Guided Maximum Diversity for Annotation-Efficient Fine-Tuning of Pretrained Cell Segmentation Models
Eiram Mahera Sheikh, Alaa Tharwat, Constanze Schwan, Wolfram Schenck
CGMD selects a small set of diverse images for fine-tuning pretrained cell segmentation models, achieving performance close to fully supervised methods with minimal annotations.
DOI 10.1109/isbi61048.2026.11515602