CLIP with Quality Captions: A Strong Pretraining for Vision Tasks.

Pavan Kumar Anasosalu Vasu Hadi Pouransari Fartash Faghri Oncel Tuzel

Published in: CoRR (2024)

Keyphrases

computer vision
high quality
visually guided
visual perception
image processing
vision system
quality measures
data sets
knowledge base
high level
information systems
visual features
transfer learning
temporal information
multi task
higher quality
service robots