An Empirical Study Into What Matters for Calibrating Vision-Language Models

Weijie Tu; Weijian Deng; Dylan Campbell; Stephen Gould; Tom Gedeon

2024 ICML ICML 2024

An Empirical Study Into What Matters for Calibrating Vision-Language Models

Abstract

No abstract available. No abstract was captured for this paper when its proceedings were scraped - most often an older edition published without one online. How the corpus is built.

Authors

Weijie Tu, Weijian Deng, Dylan Campbell, Stephen Gould, Tom Gedeon

Topics

Machine Learning > Application Areas > Domain Adaptation Artificial Intelligence > Core AI > Large Language Models Deep Learning > Learning Types > Multimodal Learning

Keywords

calibration distribution shift vision-language model uncertainty estimation temperature scaling few-shot calibration

Download PDF