Get our free extension to see links to code for papers anywhere online!

Chrome logo Add to Chrome

Firefox logo Add to Firefox

Picture for Asato Matsumoto

Can Vision Transformers Learn without Natural Images?


Mar 24, 2021
Kodai Nakashima, Hirokatsu Kataoka, Asato Matsumoto, Kenji Iwata, Nakamasa Inoue

* Project page: https://hirokatsukataoka16.github.io/Vision-Transformers-without-Natural-Images/ 

  Access Paper or Ask Questions

Pre-training without Natural Images


Jan 21, 2021
Hirokatsu Kataoka, Kazushige Okayasu, Asato Matsumoto, Eisuke Yamagata, Ryosuke Yamada, Nakamasa Inoue, Akio Nakamura, Yutaka Satoh

* ACCV 2020 Best Paper Honorable Mention Award, Codes are publicly available: https://github.com/hirokatsukataoka16/FractalDB-Pretrained-ResNet-PyTorch 

  Access Paper or Ask Questions