Progressive Network Grafting for Few-Shot Knowledge Distillation


  • Chengchao Shen Zhejiang University
  • Xinchao Wang Stevens Institute of Technology
  • Youtan Yin Zhejiang University
  • Jie Song Zhejiang University
  • Sihui Luo Zhejiang University
  • Mingli Song Zhejiang University Alibaba-Zhejiang University Joint Research Institute of Frontier Technologies



Learning & Optimization for CV, Applications, (Deep) Neural Network Algorithms, Classification and Regression


Knowledge distillation has demonstrated encouraging performances in deep model compression. Most existing approaches, however, require massive labeled data to accomplish the knowledge transfer, making the model compression a cumbersome and costly process. In this paper, we investigate the practical few-shot knowledge distillation scenario, where we assume only a few samples without human annotations are available for each category. To this end, we introduce a principled dual-stage distillation scheme tailored for few-shot data. In the first step, we graft the student blocks one by one onto the teacher, and learn the parameters of the grafted block intertwined with those of the other teacher blocks. In the second step, the trained student blocks are progressively connected and then together grafted onto the teacher network, allowing the learned student blocks to adapt themselves to each other and eventually replace the teacher network. Experiments demonstrate that our approach, with only a few unlabeled samples, achieves gratifying results on CIFAR10,CIFAR100, and ILSVRC-2012. On CIFAR10 and CIFAR100, our performances are even on par with those of knowledge distillation schemes that utilize the full datasets. The source code is available at




How to Cite

Shen, C., Wang, X., Yin, Y., Song, J., Luo, S., & Song, M. (2021). Progressive Network Grafting for Few-Shot Knowledge Distillation. Proceedings of the AAAI Conference on Artificial Intelligence, 35(3), 2541-2549.



AAAI Technical Track on Computer Vision II