Learning Transferable Visual Models From Natural Language Supervision

   Alec Radford * 1 Jong Wook Kim * 1 Chris Hallacy 1 Aditya Ramesh 1 Gabriel Goh 1 Sandhini Agarwal 1
    Girish Sastry 1 Amanda Askell 1 Pamela Mishkin 1 Jack Clark 1 Gretchen Krueger 1 Ilya Sutskever 1

              Abstract               interface (McCann et al., 2018; Radford et al., 2019; Raffel
                                et al., 2019) has enabled task-agnostic architectures to zero-
    SOTA computer vision syste ...