HSViT: Horizontally Scalable Vision Transformer

doi:doi:10.57702/q8ln2hj8

HSViT: Horizontally Scalable Vision Transformer

This paper introduces a horizontally scalable vision transformer (HSViT) scheme with a novel image-level feature embedding. The design of HSViT preserves the inductive bias from convolutional layers while effectively reducing the number of layers and parameters of the models.

Data and Resources

Original MetadataJSON
The json representation of the dataset with its distributions based on DCAT.
Explore
- Preview
- Download

Cite this as

Chenhao Xu, Chang-Tsun Li, Chee Peng Lim, Douglas Creighton (2024). Dataset: HSViT: Horizontally Scalable Vision Transformer. https://doi.org/10.57702/q8ln2hj8

DOI retrieved: December 2, 2024

Additional Info

Field	Value
Created	December 2, 2024
Last update	December 2, 2024
Author	Chenhao Xu
More Authors	Chang-Tsun Li Chee Peng Lim Douglas Creighton
Homepage	https://github.com/xuchenhao001/HSViT