Mixing Pooling Instead of Class Token Representation Learning for Vision Transformer

Autor: Zhenrui Huang, Libo Xu, Yucheng Sun, Jiagong Wang, Lingchao Zhu
Rok vydání: 2021
Zdroj: 2021 2nd International Conference on Artificial Intelligence and Computer Engineering (ICAICE).
DOI: 10.1109/icaice54393.2021.00013
Databáze: OpenAIRE