clip-vit-base-patch16

Papers using or citing this model 2

• Learning Transferable Visual Models From Natural Language Supervision 57.9K citations · 2021 · arXiv (Cornell University) · arXiv

  State-of-the-art computer vision systems are trained to predict a fixed set of predetermined object categories. This restricted form of supervision limits their generality and usability since additional labeled data is needed to specify...

• FairFace: Face Attribute Dataset for Balanced Race, Gender, and Age 218 citations · 2019 · arXiv (Cornell University) · arXiv

  Existing public face datasets are strongly biased toward Caucasian faces, and other races (e.g., Latino) are significantly underrepresented. This can lead to inconsistent model accuracy, limit the applicability of face analytic systems...