The DOI matches its Crossref record; 8 of the 8 references it cites were found in a registry or an index.
Face Model Compression by Distilling Knowledge from Neurons
Open accessAbstract
The recent advanced face recognition systems werebuilt on large Deep Neural Networks (DNNs) or theirensembles, which have millions of parameters. However, the expensive computation of DNNs make theirdeployment difficult on mobile and embedded devices. This work addresses model compression for face recognition,where the learned knowledge of a large teachernetwork or its ensemble is utilized as supervisionto train a compact student network. Unlike previousworks that represent the knowledge by the soften labelprobabilities, which are difficult to fit, we represent theknowledge by using the neurons at the higher hiddenlayer, which preserve as much information as the label probabilities, but are more compact. By leveragingthe essential characteristics (domain knowledge) of thelearned face representation, a neuron selection methodis proposed to choose neurons that are most relevant toface recognition. Using the selected neurons as supervisionto mimic the single networks of DeepID2+ andDeepID3, which are the state-of-the-art face recognition systems, a compact student with simple network structure achieves better verification accuracy on LFW than its teachers, respectively. When using an ensemble of DeepID2+ as teacher, a mimicked student is able to outperform it and achieves 51.6 times compression ratio and 90 times speed-up in inference, making this cumbersome model applicable on portable devices.
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
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
Histograms of Oriented Gradients for Human Detection
Dalal, N., & Triggs, B. (2005) · 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05) · doi:10.1109/cvpr.2005.177 · Cited by 33,584
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
Turk, M., & Pentland, A. (1991) · Journal of Cognitive Neuroscience · doi:10.1162/jocn.1991.3.1.71 · Cited by 13,733
An Introduction to Variational Methods for Graphical Models
Jordan, M. I., Ghahramani, Z., Jaakkola, T. S., & Saul, L. K. (1999) · Machine Learning · doi:10.1023/a:1007665907178 · Cited by 3,791
Popular Ensemble Methods: An Empirical Study
Opitz, D., & Maclin, R. (1999) · Journal of Artificial Intelligence Research · doi:10.1613/jair.614 · Cited by 2,953 · cited 1×
“This work is chosen as an example because it successfully incorporated multiple complex components for face recognition, such as local convolution [12], ranking loss function [19], deeply supervised learning [13], and model ensemble [17].”
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
Cited by
Knowledge 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
Relational Knowledge Distillation
Park, W., Kim, D., Lu, Y., & Cho, M. (2019) · 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2019.00409 · Cited by 1,681
A Survey of Model Compression and Acceleration for Deep Neural Networks
Cheng, Y., Wang, D., Zhou, P., & Zhang, T. (2017) · arXiv · doi:10.48550/arxiv.1710.09282 · Cited by 857
“Different from previous works which represented the knowledge using the soften label probabilities, [54] represented the knowledge by using the neurons in the higher hidden layer, which preserved as much information as the label probabilities, but are more compact.”
ResultCheng, Y., Wang, D., Zhou, P., & Zhang, T. (2018) · IEEE Signal Processing Magazine · doi:10.1109/msp.2017.2765695 · Cited by 817
MobileFaceNets: Efficient CNNs for Accurate Real-Time Face Verification on Mobile Devices
Chen, S., Liu, Y., Gao, X., & Han, Z. (2018) · Lecture Notes in Computer Science · doi:10.1007/978-3-319-97909-0_46 · Cited by 771
ISNet: Shape Matters for Infrared Small Target Detection
Zhang, M., Zhang, R., Yang, Y., Bai, H., Zhang, J., & Guo, J. (2022) · 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr52688.2022.00095 · Cited by 721
MobileBERT: a Compact Task-Agnostic BERT for Resource-Limited Devices
Sun, Z., Yu, H., Song, X., Liu, R., Yang, Y., & Zhou, D. (2020) · Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics · doi:10.18653/v1/2020.acl-main.195 · Cited by 757
Correlation Congruence for Knowledge Distillation
Peng, B., Jin, X., Li, D., Zhou, S., Wu, Y., Liu, J., Zhang, Z., & Liu, Y. (2019) · 2019 IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2019.00511 · Cited by 570
Computing Systems for Autonomous Driving: State of the Art and Challenges
Liu, L., Lu, S., Zhong, R., Wu, B., Yao, Y., Zhang, Q., & Shi, W. (2021) · IEEE Internet of Things Journal · doi:10.1109/jiot.2020.3043716 · Cited by 450
On Compressing Deep Models by Low Rank and Sparse Decomposition
Yu, X., Liu, T., Wang, X., & Tao, D. (2017) · 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2017.15 · Cited by 403
Self-citationA review of convolutional neural network architectures and their optimizations
Cong, S., & Zhou, Y. (2023) · Artificial Intelligence Review · doi:10.1007/s10462-022-10213-5 · Cited by 381
Like What You Like: Knowledge Distill via Neuron Selectivity Transfer
Huang, Z., & Wang, N. (2017) · arXiv (Cornell University) · doi:10.48550/arxiv.1707.01219 · Cited by 300
GAN Compression: Efficient Architectures for Interactive Conditional GANs
Li, M., Lin, J., Ding, Y., Liu, Z., Zhu, J.-Y., & Han, S. (2020) · 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr42600.2020.00533 · Cited by 216
Self-citationOpenEI: An Open Framework for Edge Intelligence
Zhang, X., Wang, Y., Lu, S., Liu, L., xu, L., & Shi, W. (2019) · 2019 IEEE 39th International Conference on Distributed Computing Systems (ICDCS) · doi:10.1109/icdcs.2019.00182 · Cited by 139
“[31] use the neurons in the hidden layer to generate more compact models and preserve as much of the label information as possible.”
MethodZhu, M., Tang, Y., & Han, K. (2021) · arXiv · doi:10.48550/arxiv.2104.08500 · Cited by 63
A Generalization Performance Study Using Deep Learning Networks in Embedded Systems
Gorospe, J., Mulero, R., Arbelaitz, O., Muguerza, J., & Antón, M. Á. (2021) · Sensors · doi:10.3390/s21041031 · Cited by 32
“It has also been shown that this concept can be transferred to neurons, where a group of significant neurons can play the role of the teacher [44].”
Background
Metadata
- Authors
- Luo, P., Zhu, Z., Liu, Z., Wang, X., & Tang, X.
- Venue
- Proceedings of the AAAI Conference on Artificial Intelligence
- Published
- 2016-03-05
- Volume
- 30
- Issue
- 1
- ISSN
- 2159-5399 (ISSN-L)
- 2374-3468
- OpenAlex
- W2543539599
- Cited by
- 199
- References
- 8
- FWCI
- 6.81
- Type
- conference paper
- Language
- en
- Open access
- diamond
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.