Search Results for author:
Found 2 papers, 2 papers with code
Attribute Diversity Determines the Systematicity Gap in VQA
Although modern neural networks often generalize to new combinations of familiar concepts, the conditions that enable such compositionality have long been an open question.
The Calibration Generalization Gap
We propose a systematic way to study the calibration error: by decomposing it into (1) calibration error on the train set, and (2) the calibration generalization gap.
Cannot find the paper you are looking for? You can
Submit a new open access paper.
