Work

A-ViT: Adaptive Tokens for Efficient Vision Transformer

Year: 2022

Type: conference-paper

Source: IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings

DOI: 10.1109/cvpr52688.2022.01054

Authors: Hongxu Yin, Arash Vahdat, Jose M. Alvarez, Arun Mallya, Jan Kautz, Pavlo Molchanov

Institutions: Nvidia (United Kingdom), Nvidia (United States)

Language: English

Topic: Advanced Neural Network Applications

Subfield: Computer Vision and Pattern Recognition

Field: Computer Science

Domain: Physical Sciences

Open Access status: closed

OpenAlex ID: W4312849330

FWCI: 26.2

Cites: 61

Cited by: 352

Related to: 10