Plots of predictive performance given by the area under the receiver operating curve (AUC) against finetuning training set size on a log scale.

<p>Models that did not include tumor size are represented with a <sup>†</sup>. The finetuned model (light blue bars) outperforms the baseline (dark blue) for all training set sizes, showing that self-supervised pretraining proves to be key in few-shot learning. When adding the tumo...

Full description

Saved in:
Bibliographic Details
Main Author: Vesna Barros (13876436) (author)
Other Authors: Nour Abdallah (21453774) (author), Michal Ozery-Flato (10684974) (author), Avihu Dekel (21453777) (author), Moshiko Raboh (21453780) (author), Nicholas Heller (13147303) (author), Simona Rabinovici-Cohen (21453783) (author), Alex Golts (21453786) (author), Amilcare Gentili (20515670) (author), Daniel Lang (78835) (author), Suman Chaudhary (349511) (author), Varsha Satish (21453789) (author), Resha Tejpaul (3370376) (author), Ivan Eggel (21453792) (author), Itai Guez (21453795) (author), Ella Barkan (21453798) (author), Henning Müller (3266811) (author), Efrat Hexter (21453801) (author), Michal Rosen-Zvi (238425) (author), Christopher Weight (21453804) (author)
Published: 2025
Subjects:
Tags: Add Tag
No Tags, Be the first to tag this record!