Zobrazeno 1 - 1
of 1
pro vyhledávání: '"Sora Takashima"'
Autor:
Hirokatsu Kataoka, Ryo Hayamizu, Ryosuke Yamada, Kodai Nakashima, Sora Takashima, Xinyu Zhang, Edgar Josafat Martinez-Noriega, Nakamasa Inoue, Rio Yokota
In the present work, we show that the performance of formula-driven supervised learning (FDSL) can match or even exceed that of ImageNet-21k without the use of real images, human-, and self-supervision during the pre-training of Vision Transformers (
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::e20112254f6b8e1188961a5292ed0915
