@misc{li2021improved, title={Improved Multiscale Vision Transformers for Classification and Detection}, author={Yanghao Li and Chao-Yuan Wu and Haoqi Fan and Karttikeya Mangalam and Bo Xiong and Jitendra Malik and Christoph Feichtenhofer}, year={2021}, eprint={2112.01526}, archivePrefix={arXiv}, primaryClass={cs.CV}, url={https://arxiv.org/abs/2112.01526} }