MAXViT: MaxViT: Multi-Axis Vision Transformer (ECCV 2022)
This repository hosts the TensorFlow implementation of MAXViT paper.
Disclaimer: This is not an officially supported Google product.
Should you find this repository useful, please consider citing:
@article{tu2022maxvit,
title={MaxViT: Multi-Axis Vision Transformer},
author={Tu, Zhengzhong and Talebi, Hossein and Zhang, Han and Yang, Feng and Milanfar, Peyman and Bovik, Alan and Li, Yinxiao},
journal={ECCV},
year={2022},
}
This repository is built on the EfficientNet and CoAtNet.