CvT

This is an official implementation of CvT: Introducing Convolutions to Vision Transformers. We present a new architecture, named Convolutional vision Transformers (CvT), that improves Vision Transformers (ViT) in performance and efficienty by introducing convolutions into ViT to yield the best of both designs. This is accomplished through two primary modifications: a hierarchy of Transformers containing a new convolutional token embedding, and a convolutional Transformer block leveraging a convolutional projection. These changes introduce desirable properties of convolutional neural networks (CNNs) to the ViT architecture (e.g. shift, scale, and distortion invariance) while maintaining the merits of Transformers (e.g. dynamic attention, global context, and better generalization). We validate CvT by conducting extensive experiments, showing that this approach achieves state-of-the-art performance over other Vision Transformers and ResNets on ImageNet-1k, with fewer parameters and lower FLOPs. In addition, performance gains are maintained when pretrained on larger dataset (e.g. ImageNet-22k) and fine-tuned to downstream tasks.