Data Level Lottery Ticket Hypothesis for Vision Transformers

The conventional lottery ticket hypothesis (LTH) claims that there exists a sparse subnetwork within a dense neural network and a proper random initial-ization method called the winning ticket, such that it can be trained from scratch to almost as good as the dense counterpart.

Data and Resources

Cite this as

Xuan Shen, Zhenglun Kong, Minghai Qin, Peiyan Dong, Geng Yuan, Xin Meng, Hao Tang, Xiaolong Ma, Yanzhi Wang (2024). Dataset: Data Level Lottery Ticket Hypothesis for Vision Transformers. https://doi.org/10.57702/jdt06eal

DOI retrieved: December 16, 2024

Additional Info

Field Value
Created December 16, 2024
Last update December 16, 2024
Author Xuan Shen
More Authors
Zhenglun Kong
Minghai Qin
Peiyan Dong
Geng Yuan
Xin Meng
Hao Tang
Xiaolong Ma
Yanzhi Wang
Homepage https://github.com/shawnricecake/vit-lottery-ticket-input