Explaining CLIP's performance disparities on data from blind/low vision users

no code implementations • 29 Nov 2023 • Daniela Massiceti, Camilla Longden, Agnieszka Słowik, Samuel Wills, Martin Grayson, Cecily Morrison

Testing 25 CLIP variants in a zero-shot classification task, we find that their accuracy is 15 percentage points lower on average for images captured by BLV users than web-crawled images.

Few-Shot Learning Zero-Shot Learning