FitNets: Hints for Thin Deep Nets

By Adriana Romero, Nicolas Ballas, Samira Ebrahimi Kahou, Antoine Chassang, Carlo Gatta, Yoshua Bengio. 2014

4,770 citations recorded by the source corpus.

While depth tends to improve network performances, it also makes gradient-based training more difficult since deeper networks tend to be more non-linear. The recently proposed knowledge distillation approach is aimed at obtaining small and fast-to-execute models, and it has shown that a student network could imitate the soft output of a larger teacher network or ensemble of networks. In this paper, we extend this idea to allow the training of a student that is deeper and thinner than the teacher, using not only the outputs but also the intermediate representations learned by the teacher as hints to improve the training process and final performance of the student. Because the student intermediate hidden layer will generally be smaller than the teacher's intermediate hidden layer, additional parameters are introduced to map the student hidden layer to the prediction of the teacher hidden layer. This allows one to train deeper students that can generalize better or run faster, a trade-off that is controlled by the chosen student capacity. For example, on CIFAR-10, a deep student network with almost 10.4 times less parameters outperforms a larger, state-of-the-art teacher network.

Subfields: Artificial Intelligence, Computer Vision and Pattern Recognition, Model Architectures, Efficiency & Compression

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

  1. Dacheng Tao
  2. Yoshua Bengio
  3. Mohit Bansal
  4. Jianfeng Gao
  5. Quoc V. Le
  6. Sergey Levine
  7. Percy Liang
  8. Trevor Darrell

In Computer Vision and Pattern Recognition

  1. Luc Van Gool
  2. Dacheng Tao
  3. Xiaogang Wang
  4. Ming-Hsuan Yang
  5. Trevor Darrell
  6. Yi Yang
  7. Jitendra Malik
  8. Bernt Schiele

In Model Architectures

  1. Yoshua Bengio
  2. Quoc V. Le
  3. Alan L. Yuille
  4. Dacheng Tao
  5. Kaiming He
  6. Xiaogang Wang
  7. Jiashi Feng
  8. Chunhua Shen

In Efficiency & Compression

  1. Song Han
  2. Dacheng Tao
  3. Kurt Keutzer
  4. Yunhe Wang
  5. Yi Yang
  6. Zi-Mei Yao
  7. Greg Mori
  8. Frederick Tung

Citations in the corpus