ConvNets Match Vision Transformers at Scale
— Tanishq Mathew Abraham, PhD (@iScienceLuvr) October 26, 2023
abs: https://t.co/dUs2I06B9d
This paper from Google DeepMind pretrains a variety of NFNet models on the JFT-4B at various scales and obtain performance on ImageNet similar to ViTs.
> Our work reinforces the bitter lesson. The most… pic.twitter.com/vgG7LI4PD3
No comments:
Post a Comment