Work

FastViT: Real-Time Linear Attention Accelerator for Dense Predictions of Vision Transformer (ViT)

Year: 2025

Type: conference-paper

Source: IEEE International Symposium on Circuits and Systems proceedings

DOI: 10.1109/iscas56072.2025.11043624

Authors: Zhuoheng Ran, Zewen Ye, Chong Wu, Ray C.C. Cheung, Hong Yan

Institutions: City University of Hong Kong, Zhejiang University

Language: English

Topic: Advanced Neural Network Applications

Subfield: Computer Vision and Pattern Recognition

Field: Computer Science

Domain: Physical Sciences

SDG: Industry, innovation and infrastructure

Open Access status: closed

Funders: Innovation and Technology Commission, University of Hong Kong

OpenAlex ID: W4411726481

FWCI: 1.592

Cites: 34

Cited by: 2

Related to: 10