An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale

The Vision Transformer (ViT) splits an image into patches, treats each patch as a token and feeds the sequence to a standard Transformer encoder, with no convolutions.

Why it matters

With enough pre-training data it matched or beat CNNs, which brought Transformers into computer vision and toward unified multimodal models.

Read the paper: arXiv:2010.11929

Plain-language summary written by SolxLab. Read the full paper at the official link; all rights remain with the authors.