Fig. 4: Performance for different percentages of pretraining data (mean).
From: 3D foundation model for generalizable disease detection in head computed tomography
We compared label efficiency in terms of different percentages of pretraining data for MAE vs DINO. The 95% CIs are plotted in colour bands and the centre points of the bands indicate the mean value. We show that although DINO presents higher label efficiency, both MAE and DINO efficiently scale up on downstream performance as more pretraining data are incorporated.
