Student or educator? Sign up with your school email and get 6 months of Pro free.
CoChat
Sign Up
Cited by 1,570

The DOI matches its Crossref record; 13 of the 13 references it cites were found in a registry or an index.

A Gift from Knowledge Distillation: Fast Optimization, Network Minimization and Transfer Learning

Yim, Junho, Joo, Donggyu, Bae, Jihoon, Kim, Junmo·2017·2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)
DOI 10.1109/cvpr.2017.754
Open this paper in CoChat — free account

Abstract

We introduce a novel technique for knowledge transfer, where knowledge from a pretrained deep neural network (DNN) is distilled and transferred to another DNN. As the DNN performs a mapping from the input space to the output space through many layers sequentially, we define the distilled knowledge to be transferred in terms of flow between layers, which is calculated by computing the inner product between features from two layers. When we compare the student DNN and the original network with the same size as the student DNN but trained without a teacher network, the proposed method of transferring the distilled knowledge as the flow between two layers exhibits three important phenomena: (1) the student DNN that learns the distilled knowledge is optimized much faster than the original model, (2) the student DNN outperforms the original DNN, and (3) the student DNN can learn the distilled knowledge from a teacher DNN that is trained at a different task, and the student DNN outperforms the original DNN that is trained from scratch.

Overview

The claims and statistics of this paper haven’t been checked yet.

Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.

A few free checks a day · papers already verified open instantly · results are public

Integrity signals

Registry

Crossref · 10.1109/cvpr.2017.754

Cites

13 of 13 references verified0 citation errors · 0 not checkable

Statistics

Verification

Claims the paper makes

The claims and statistics of this paper haven’t been checked yet.

Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.

A few free checks a day · papers already verified open instantly · results are public

Self-check

Percentages, sums and reported differences re-computed from the paper’s own numbers.

The self-check needs the paper’s full text.

Citations

Cites

Show all 13 references

Research works printed but not linked: 16

  1. krähenbühl, 2015, Data-dependent initializations of convolutional neural networks
  2. krizhevsky, 2009, Learning multiple layers of features from tiny images
  3. mishkin, 2015, All you need is a good init
  4. noh, 2015, Image question answering using convolutional neural network with dynamic parameter prediction
  5. zhou, 2015, Simple baseline for visual question answering
  6. duchi, 2011, Adaptive subgradient methods for online learning and stochastic optimization, Journal of Machine Learning Research, 12, 2121
  7. chen, 2015, Net2net Accelerating learning via knowledge transfer
  8. gatys, 2015, A neural algorithm of artistic style
  9. erhan, 2010, Why does unsupervised pre-training help deep learning?, Journal of Machine Learning Research, 11, 625
  10. glorot, 2010, Understanding the difficulty of training deep feedforward neural networks, AISTATS, 9, 249
  11. branson, 2014, Bird species categorization using pose normalized deep convolutional nets
  12. romero, 2015, Fitnets: Hints for thin deep nets, Proceedings of ICL
  13. saxe, 2013, Exact solutions to the nonlinear dynamics of learning in deep linear neural networks
  14. veit, 2016, Residual networks are exponential ensembles of relatively shallow networks
  15. 10.1109/CVPR.2015.7298594 · DOI · Paper page
  16. wah, 2011, The Caltech-UCSD Birds-200-2011 Dataset, Technical Report

Cited by

Metadata

Authors
Yim, J., Joo, D., Bae, J., & Kim, J.
Venue
2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)
Publisher
IEEE
Published
2017-07
Pages
7130-7138
ISSN
1063-6919 (ISSN-L)
DOI
10.1109/cvpr.2017.754
OpenAlex
W2739879705
Cited by
1,570
References
13
FWCI
45.73
Type
conference paper
Language
en
Open access
closed

About these checks

Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.

Statistics and arithmetic are recomputed, not judged.

Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.

What counts as a claim ›How we measure confidence ›How we check this ›

Are you an author, or do you see a problem with this page? Request a review

Data sources

Bibliographic data: Semantic Scholar, OpenAlex, Crossref.

Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).

Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.