Vit l16

The classification variant of the Vision Transformer (ViT) version L16 architecture.

Warning

The ViT architectures only work for RGB encoding (channel size = 3).

Architecture Variable	Value
Key in architecture_dict	"2D.ViT_L16"
Input_shape	(384, 384)
Standardization	"tf"

Reference - Implementation

Fausto Morales; https://github.com/faustomorales
https://github.com/faustomorales/vit-keras

Vo Van Tu; https://github.com/tuvovan
https://github.com/tuvovan/Vision_Transformer_Keras

Original: Google Research
https://github.com/google-research/vision_transformer

Reference - Publication

@article{dosovitskiy2020vit,
  title={An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale},
  author={Dosovitskiy, Alexey and Beyer, Lucas and Kolesnikov, Alexander and Weissenborn, Dirk and Zhai, Xiaohua and Unterthiner, Thomas and  Dehghani, Mostafa and Minderer, Matthias and Heigold, Georg and Gelly, Sylvain and Uszkoreit, Jakob and Houlsby, Neil},
  journal={ICLR},
  year={2021}
}

@article{tolstikhin2021mixer,
  title={MLP-Mixer: An all-MLP Architecture for Vision},
  author={Tolstikhin, Ilya and Houlsby, Neil and Kolesnikov, Alexander and Beyer, Lucas and Zhai, Xiaohua and Unterthiner, Thomas and Yung, Jessica and Steiner, Andreas and Keysers, Daniel and Uszkoreit, Jakob and Lucic, Mario and Dosovitskiy, Alexey},
  journal={arXiv preprint arXiv:2105.01601},
  year={2021}
}

@article{steiner2021augreg,
  title={How to train your ViT? Data, Augmentation, and Regularization in Vision Transformers},
  author={Steiner, Andreas and Kolesnikov, Alexander and and Zhai, Xiaohua and Wightman, Ross and Uszkoreit, Jakob and Beyer, Lucas},
  journal={arXiv preprint arXiv:2106.10270},
  year={2021}
}

@article{chen2021outperform,
  title={When Vision Transformers Outperform ResNets without Pretraining or Strong Data Augmentations},
  author={Chen, Xiangning and Hsieh, Cho-Jui and Gong, Boqing},
  journal={arXiv preprint arXiv:2106.01548},
  year={2021},
}

@article{zhai2022lit,
  title={LiT: Zero-Shot Transfer with Locked-image Text Tuning},
  author={Zhai, Xiaohua and Wang, Xiao and Mustafa, Basil and Steiner, Andreas and Keysers, Daniel and Kolesnikov, Alexander and Beyer, Lucas},
  journal={CVPR},
  year={2022}
}