Be your own teacher: improve the performance of convolutional neural networks via self distillation

Linfeng Zhang Institute for Interdisciplinary Information Sciences, Tsinghua University Jiebo Song Institute for Interdisciplinary Information Core Technology Anni Gao Institute for Interdisciplinary Information Core Technology Jingwei Chen HiSilicon Chenglong Bao Yau Mathematical Sciences Center, Tsinghua University Kaisheng Ma Institute for Interdisciplinary Information Sciences, Tsinghua University

TBD mathscidoc:2206.43019

ICCV, 2019.10
Convolutional neural networks have been widely deployed in various application scenarios. In order to extend the applications’ boundaries to some accuracy-crucial domains, researchers have been investigating approaches to boost accuracy through either deeper or wider network structures, which brings with them the exponential increment of the computational and storage cost, delaying the responding time. In this paper, we propose a general training framework named self distillation, which notably enhances the performance (accuracy) of convolutional neural networks through shrinking the size of the network rather than aggrandizing it. Different from traditional knowledge distillation - a knowledge transformation methodology among networks, which forces student neural networks to approximate the softmax layer outputs of pre-trained teacher neural networks, the proposed self distillation framework distills knowledge within network itself. The networks are firstly divided into several sections. Then the knowledge in the deeper portion of the networks is squeezed into the shallow ones. Experiments further prove the generalization of the proposed self distillation framework: enhancement of accuracy at average level is 2.65%, varying from 0.61% in ResNeXt as minimum to 4.07% in VGG19 as maximum. In addition, it can also provide flexibility of depth-wise scalable inference on resource-limited edge devices. Our codes have been released on github. https://github.com/ArchipLab-LinfengZhang/ pytorch-self-distillation.
No keywords uploaded!
[ Download ] [ 2022-06-16 15:33:38 uploaded by Baocl ] [ 298 downloads ] [ 0 comments ]
@inproceedings{linfeng2019be,
  title={Be your own teacher: improve the performance of convolutional neural networks via self distillation},
  author={Linfeng Zhang, Jiebo Song, Anni Gao, Jingwei Chen, Chenglong Bao, and Kaisheng Ma},
  url={http://archive.ymsc.tsinghua.edu.cn/pacm_paperurl/20220616153338947977378},
  booktitle={ICCV},
  year={2019},
}
Linfeng Zhang, Jiebo Song, Anni Gao, Jingwei Chen, Chenglong Bao, and Kaisheng Ma. Be your own teacher: improve the performance of convolutional neural networks via self distillation. 2019. In ICCV. http://archive.ymsc.tsinghua.edu.cn/pacm_paperurl/20220616153338947977378.
Please log in for comment!
 
 
Contact us: office-iccm@tsinghua.edu.cn | Copyright Reserved