CatLIP: CLIP-level Visual Recognition Accuracy with 2.7× Faster Pre-training on Web-scale Image-Text Data
AuthorsSachin Mehta, Max Horton, Fartash Faghri, Mohammad Sekhavat, Mahyar Najibikohnehshahri, Mehrdad Farajtabar, Oncel Tuzel, Mohammad Rastegari