The DOI matches its Crossref record; 34 of the 34 references it cites were found in a registry or an index.
Learning from Multiple Teacher Networks
Abstract
Training thin deep networks following the student-teacher learning paradigm has received intensive attention because of its excellent performance. However, to the best of our knowledge, most existing work mainly considers one single teacher network. In practice, a student may access multiple teachers, and multiple teacher networks together provide comprehensive guidance that is beneficial for training the student network. In this paper, we present a method to train a thin deep network by incorporating multiple teacher networks not only in output layer by averaging the softened outputs (dark knowledge) from different networks, but also in the intermediate layers by imposing a constraint about the dissimilarity among examples. We suggest that the relative dissimilarity between intermediate representations of different examples serves as a more flexible and appropriate guidance from teacher networks. Then triplets are utilized to encourage the consistence of these relative dissimilarity relationships between the student network and teacher networks. Moreover, we leverage a voting strategy to unify multiple relative dissimilarity information provided by multiple teacher networks, which realizes their incorporation in the intermediate layers. Extensive experimental results demonstrated that our method is capable of generating a well-performed student network, with the classification accuracy comparable or even superior to all teacher networks, yet having much fewer parameters and being much faster in running.
Overview
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
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
Deep Residual Learning for Image Recognition
He, K., Zhang, X., Ren, S., & Sun, J. (2016) · 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2016.90 · Cited by 235,474
Very Deep Convolutional Networks for Large-Scale Image Recognition
Simonyan, K., & Zisserman, A. (2014) · arXiv · doi:10.48550/arxiv.1409.1556 · Cited by 114,148
ImageNet classification with deep convolutional neural networks
Krizhevsky, A., Sutskever, I., & Hinton, G. E. (2017) · Communications of the ACM · doi:10.1145/3065386 · Cited by 112,155
Going deeper with convolutions
Szegedy, C., Liu, W., Jia, Y., Sermanet, P., Reed, S., Anguelov, D., Erhan, D., Vanhoucke, V., & Rabinovich, A. (2015) · 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2015.7298594 · Cited by 48,562
Proceedings of IEEE Conference on Computer Vision and Pattern Recognition
(1993) · doi:10.1109/cvpr.1993 · Cited by 17,667
A fast learning algorithm for deep belief nets
Hinton, G. E., Osindero, S., & Teh, Y.-W. (2006) · Neural Computation · doi:10.1162/neco.2006.18.7.1527 · Cited by 16,336
FaceNet: A unified embedding for face recognition and clustering
Schroff, F., Kalenichenko, D., & Philbin, J. (2015) · 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2015.7298682 · Cited by 15,267
Distilling the Knowledge in a Neural Network
Hinton, G., Vinyals, O., & Dean, J. (2015) · arXiv · doi:10.48550/arxiv.1503.02531 · Cited by 14,204
Representation Learning: A Review and New Perspectives
Bengio, Y., Courville, A., & Vincent, P. (2013) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2013.50 · Cited by 13,001
Greedy layer-wise training of deep networks
Bengio, Y., Lamblin, P., Popovici, D., & Larochelle, H. (2007) · Advances in Neural Information Processing Systems 19 · doi:10.7551/mitpress/7503.003.0024 · Cited by 4,841 · cited 1×
“Without the help of a teacher network, some algorithms used pre-training strategy to train the network layer by layer and initialized the network with a potentially good start in supervised manner [3] or unsupervised manner [3, 16].”
MethodFitNets: Hints for Thin Deep Nets
Romero, A., Ballas, N., Kahou, S. E., Chassang, A., Gatta, C., & Bengio, Y. (2014) · arXiv · doi:10.48550/arxiv.1412.6550 · Cited by 2,859
Deep Metric Learning Using Triplet Network
Hoffer, E., & Ailon, N. (2015) · Lecture Notes in Computer Science · doi:10.1007/978-3-319-24261-3_7 · Cited by 2,134
Courbariaux, M., Hubara, I., Soudry, D., El-Yaniv, R., & Bengio, Y. (2016) · arXiv · doi:10.48550/arxiv.1602.02830 · Cited by 2,106
Buciluǎ, C., Caruana, R., & Niculescu-Mizil, A. (2006) · Proceedings of the 12th ACM SIGKDD international conference on Knowledge discovery and data mining · doi:10.1145/1150402.1150464 · Cited by 2,068
Do Deep Nets Really Need to be Deep?
Ba, J. L., & Caruana, R. (2013) · arXiv (Cornell University) · doi:10.48550/arxiv.1312.6184 · Cited by 1,335
Lee, C., Xie, S., Gallagher, P., Zhang, Z., & Zhuowen Tu, A. (2014) · arXiv (Cornell University) · doi:10.48550/arxiv.1409.5185 · Cited by 993
An empirical evaluation of deep architectures on problems with many factors of variation
Larochelle, H., Erhan, D., Courville, A., Bergstra, J., & Bengio, Y. (2007) · Proceedings of the 24th international conference on Machine learning · doi:10.1145/1273496.1273556 · Cited by 992
Compressing Neural Networks with the Hashing Trick
Chen, W., Wilson, J. T., Tyree, S., Weinberger, K. Q., & Chen, Y. (2015) · arXiv · doi:10.48550/arxiv.1504.04788 · Cited by 974
Compressing Deep Convolutional Networks using Vector Quantization
Gong, Y., Liu, L., Yang, M., & Bourdev, L. D. (2014) · arXiv (Cornell University) · doi:10.48550/arxiv.1412.6115 · Cited by 925
Deeplysupervised netsPreprint
Lee, C., Xie, S., Gallagher, P., Zhang, Z., & Tu, Z. (2015) · Cited by 849
Sparse Convolutional Neural Networks
Liu, B., Wang, M., Foroosh, H., Tappen, M., & Penksy, M. (2015) · 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2015.7298681 · Cited by 680
On the Complexity of Best Arm Identification in Multi-Armed Bandit Models
Kaufmann, E., Cappé, O., & Garivier, A. (2014) · arXiv (Cornell University) · doi:10.48550/arxiv.1407.4443 · Cited by 661
Deep Learning via Semi-supervised Embedding
Weston, J., Ratle, F., Mobahi, H., & Collobert, R. (2012) · Lecture Notes in Computer Science · doi:10.1007/978-3-642-35289-8_34 · Cited by 534
The Difficulty of Training Deep Architectures and the Effect of Unsupervised Pre-Training
Erhan, D., Manzagol, P.-A., Bengio, Y., Samy Bengio, A., & Vincent, P. (2009) · International Conference on Artificial Intelligence and Statistics · Cited by 525
Predicting Parameters in Deep Learning
Shakibi, B. (2014) · University of British Columbia · doi:10.14288/1.0165555 · Cited by 462
Multi-View Intact Space Learning
Xu, C., Tao, D., & Xu, C. (2015) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2015.2417578 · Cited by 395
Self-citationConvolutional Neural Networks Applied to House Numbers Digit Classification
Sermanet, P., Chintala, S., & LeCun, Y. (2012) · arXiv (Cornell University) · doi:10.48550/arxiv.1204.3968 · Cited by 331
Unifying distillation and privileged information
Lopez-Paz, D., Bottou, L., Schölkopf, B., & Vapnik, V. (2015) · arXiv · doi:10.48550/arxiv.1511.03643 · Cited by 270 · cited 1×
“Like the generalized distillation [23], our method also can be extended to semi-supervised cases.”
MethodLarge-Margin Multi-ViewInformation Bottleneck
Xu, C., Tao, D., & Xu, C. (2014) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2013.2296528 · Cited by 257
Self-citationCNNpack: packing convolutional neural networks in the frequency domain
Wang, Y., Xu, C., You, S., Tao, D., & Xu, C. (2016) · neural information processing systems · Cited by 180
Self-citationKnowledge Matters: Importance of Prior Information for OptimizationPreprint
Gülçehre, Ç., & Bengio, Y. (2013) · arXiv (Cornell University) · doi:10.48550/arxiv.1301.4083 · Cited by 140
Deep Model Based Transfer and Multi-Task Learning for Biological Image Analysis
Zhang, W., Li, R., Zeng, T., Sun, Q., Kumar, S., Ye, J., & Ji, S. (2015) · ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD) · doi:10.1145/2783258.2783304 · Cited by 116
(2017) · doi:10.3389/fncom.2016.00131 · Cited by 59 · cited 3×
“Different from FitNets [26] and RDL [24], we suggest that the relative dissimilarity between feature maps of different examples generated by intermediate layers serves as a more flexible and appropriate guidance from teacher networks.”
BackgroundMethodStructural Neighborhood Based Classification of Nodes in a Network
Nandanwar, S., & Murty, M. N. (2016) · ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD) · doi:10.1145/2939672.2939782 · Cited by 59
Cited by
GhostNet: More Features From Cheap Operations
Han, K., Wang, Y., Tian, Q., Guo, J., Xu, C., & Xu, C. (2020) · 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr42600.2020.00165 · Cited by 5,222
Self-citationKnowledge Distillation: A Survey
Gou, J., Yu, B., Maybank, S. J., & Tao, D. (2021) · International Journal of Computer Vision · doi:10.1007/s11263-021-01453-z · Cited by 3,931
Self-citationGrad-CAM++: Generalized Gradient-Based Visual Explanations for Deep Convolutional Networks
Chattopadhay, A., Sarkar, A., Howlader, P., & Balasubramanian, V. N. (2018) · 2018 IEEE Winter Conference on Applications of Computer Vision (WACV) · doi:10.1109/wacv.2018.00097 · Cited by 3,639
A Survey of Quantization Methods for Efficient Neural Network Inference
Gholami, A., Kim, S., Dong, Z., Yao, Z., Mahoney, M. W., & Keutzer, K. (2022) · Low-Power Computer Vision · doi:10.1201/9781003162810-13 · Cited by 1,219
“The choices of teacher models are also well studied, where [227, 265] use multiple teacher models to jointly supervise the student model, while [43, 269] apply self-distillation without an extra teacher model.”
Improved Knowledge Distillation via Teacher Assistant
Mirzadeh, S. I., Farajtabar, M., Li, A., Levine, N., Matsukawa, A., & Ghasemzadeh, H. (2020) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v34i04.5963 · Cited by 101
“You et al. (2017) proposed a voting strategy to unify multiple relative dissimilarity information provided by multiple teacher networks.”
Background
Metadata
- Authors
- You, S., Xu, C., Xu, C., & Tao, D.
- Venue
- Proceedings of the 23rd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining
- Publisher
- ACM
- Published
- 2017-08-04
- Pages
- 1285-1294
- OpenAlex
- W2743289088
- Cited by
- 395
- References
- 34
- FWCI
- 5.50
- 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.