PF-ViT: Parallel and Fast Vision Transformer for Offline Handwritten Chinese Character Recognition

Recently, Vision Transformer (ViT) has been widely used in the field of image recognition. Unfortunately, the ViT model repeatedly stacks 12-layer encoders, resulting in a large number of model computations, many parameters, and slow training speed, making it difficult to deploy on mobile devices. I...

Descripción completa

Detalles Bibliográficos
Autores principales: Dan, Yongping, Zhu, Zongnan, Jin, Weishou, Li, Zhuo
Formato: Online Artículo Texto
Lenguaje:English
Publicado: Hindawi 2022
Materias:
Research Article
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9534625/
https://www.ncbi.nlm.nih.gov/pubmed/36211021
http://dx.doi.org/10.1155/2022/8255763

Internet

https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9534625/
https://www.ncbi.nlm.nih.gov/pubmed/36211021
http://dx.doi.org/10.1155/2022/8255763

Ejemplares similares