DeepMind Proposes Novel Vision Transformer for Arbitrary Size & Resolution

In a new paper Patch n' Pack: NaViT, a Vision Transformer for any Aspect Ratio and Resolution, a Google DeepMind research team further improves ViT with Native Resolution ViT (NaViT), which is able process input sequences of arbitrary resolutions and aspect ratios.

ai artificial intelligence computer vision & graphics deepmind deepmind research deep-neural-networks google google deepmind machine learning machine learning & data science ml novel paper process research research team team technology transformer vision vision-transformer vit