DeepMind Verifies ConvNets Can Match Vision Transformers at Scale

In a new paper ConvNets Match Vision Transformers at Scale, a Google DeepMind research team challenges the prevailing belief that Vision Transformers possess superior scaling capabilities compared to ConvNets and provides empirical results revealing that ConvNets can indeed hold their own against Vision Transformers at scale.

ai artificial intelligence belief capabilities challenges convolutional neural network deepmind deepmind research deep-neural-networks google google deepmind indeed machine learning machine learning & data science match ml paper research research team scale scaling team technology transformers vision vision-transformer vision transformers