Self-Supervised Versus Supervised Training for Segmentation of Organoid Images

no code implementations • 19 Nov 2023 • Asmaa Haja, Eric Brouwer, Lambert Schomaker

When trained on only 114 images for the main task, the self-supervised learning approach outperforms the supervised method achieving an F1-score of 0. 85, with higher stability, in contrast to an F1=0. 78 scored by the supervised method.

Image Segmentation Self-Supervised Learning +2