Pruning Self-attentions into Convolutional Layers in Single Path

This is the official repository for our paper: Pruning Self-attentions into Convolutional Layers in Single Path by Haoyu He, Jing liu, Zizheng Pan, Jianfei Cai, Jing Zhang, Dacheng Tao and Bohan Zhuang.


To reduce the massive computational resource consumption for ViTs and add convolutional inductive bias, our SPViT prunes pre-trained ViT models into accurate and compact hybrid models by pruning self-attentions into convolutional layers. Thanks to the proposed weight-sharing scheme between self-attention and convolutional layers that cast the search problem as finding which subset of parameters to use, our SPViT has significantly reduced search cost.

Getting started:

In this repository, we provide code for pruning two representative ViT models.

If you find our paper useful, please consider cite:

  title={Pruning Self-attentions into Convolutional Layersin Single Path},
  author={He, Haoyu and Liu, Jing and Pan, Zizheng and Cai, Jianfei and Zhang, Jing and Tao, Dacheng and Zhuang, Bohan},
  journal={arXiv preprint arXiv:2111.11802},


View Github