Vision Transformers - Groups

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...

Dataset
JSON

DINOv2

The dataset used in the paper is DINOv2, a vision foundation model trained on a large-scale dataset.

Dataset
JSON

DINO dataset

The DINO dataset: A large-scale vision transformer dataset

Dataset
JSON

3 datasets found

TPC-ViT: Token Propagation Controller for Efficient Vision Transformers

DINOv2

DINO dataset