Scaling Up Visual and Vision-Language Representation Learning With Noisy Text Supervision

ScalingUpVisualandVision-LanguageRepresentationLearningWithNoisyTextSupervisionChaoJia1YinfeiYang1YeXia1Yi-TingChen1ZaranaParekh1HieuPham1QuocV.Le1YunhsuanSung1ZhenLi1TomDuerig1Abstract1.Introducti...