Tweeted By @MichaelAuli
New work on efficient self-supervised learning: data2vec 2.0 pre-trains vision models 16.4x faster than the most popular existing algorithm.
— Michael Auli (@MichaelAuli) December 13, 2022
Blog: https://t.co/pz6XWKOGGh
Paper: https://t.co/x4kgTbMj7t
Code/models: https://t.co/DoUxCzkHEX
with @ZloiAlexei @mhnt1580 @arunbabu1234 pic.twitter.com/zFHnpOo4iI