-
TPC-ViT: Token Propagation Controller for Efficient Vision Transformers
Vision transformers (ViTs) have achieved promising results on a variety of Computer Vision tasks, however their quadratic complexity in the number of input tokens has limited... -
ImageNet-1K, ADE20K, and COCO 2017
The dataset used in the paper is ImageNet-1K, ADE20K, and COCO 2017. -
ImageNet-1K and MS COCO
The dataset used in the paper is ImageNet-1K and MS COCO. -
CIFAR-10, CIFAR-100 and ImageNet-1K
The dataset used in the paper is CIFAR-10, CIFAR-100 and ImageNet-1K.
