This is a official repository of SimViT. We will open our models and codes about object detection and semantic segmentation soon. Our code references the PVT, thanks a lot for their outstanding work! For details see SimViT: Exploring a Simple Vision Transformer with sliding windows.
If you use this code for a paper, please cite:
SimViT
@misc{li2021simvit,
title={SimViT: Exploring a Simple Vision Transformer with sliding windows},
author={Gang Li and Di Xu and Xing Cheng and Lingyu Si and Changwen Zheng},
year={2021},
eprint={2112.13085},
archivePrefix={arXiv},
primaryClass={cs.CV}
}
This repo is currently maintained by Gang Li(@ucasligang).