Dataset

CVPR2022 Pretrained models for ViT

This is a set of pre-trained models for Vision Transformers which are trained on ExFractalDB-21k and RCDB-21k.
PyTorch model saving format
Creator :
Hirokatsu Kataoka, Ryo Hayamizu, Ryosuke Yamada, Kodai Nakashima, Sora Takashima, Xinyu Zhang, Edgar Josafat Martinez-Noriega, Nakamasa Inoue, Rio Yokota
License :
First Publication Date : Sun, 12 Jun 2022 JST
Citation :
  • Hirokatsu Kataoka, Ryo Hayamizu, Ryosuke Yamada, Kodai Nakashima, Sora Takashima, Xinyu Zhang, Edgar Josafat Martinez-Noriega, Nakamasa Inoue, Rio Yokota, Replacing Labeled Real-Image Datasets With Auto-Generated Contours, Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern, Recognition (CVPR), pp.21232-21241, 2022.
Tue, 30 Aug 2022 16:40:51 JST