Robustifying Vision Transformer without Retraining from Scratch

Vision Transformer (ViT) is becoming more popular in image processing. We investigate the effectiveness of test-time adaptation (TTA) on ViT, a technique that has emerged to correct its prediction during test-time by itself.

Data and Resources

Cite this as

Takeshi Kojima, Yutaka Matsuo, Yusuke Iwasawa (2024). Dataset: Robustifying Vision Transformer without Retraining from Scratch. https://doi.org/10.57702/srr812q3

DOI retrieved: December 2, 2024

Additional Info

Field Value
Created December 2, 2024
Last update December 2, 2024
Author Takeshi Kojima
More Authors
Yutaka Matsuo
Yusuke Iwasawa
Homepage https://arxiv.org/abs/2203.12345