Predicting classification accuracy when adding new unobserved classes
Published in Proceedings of the International Conference on Learning Representations (ICLR), 2021
Recommended citation: Slavutsky, Y., & Benjamini, Y. (2021). "Predicting classification accuracy when adding new unobserved classes." International Conference on Learning Representations (ICLR).
In this work we study how a few-shot classifier’s performance over an initial class set can be used to extrapolate its expected accuracy on a larger, unobserved set of classes.