Skip to main content

2020 | OriginalPaper | Buchkapitel

Knowledge Distillation Based on Pruned Model

verfasst von : Cailing Liu, Hongyi Zhang, Deyi Chen

Erschienen in: Blockchain and Trustworthy Systems

Verlag: Springer Singapore

Aktivieren Sie unsere intelligente Suche, um passende Fachinhalte oder Patente zu finden.

search-config
loading …

Abstract

The high computational complexity of deep neural networks makes them challenging to deploy in practical applications. Recent efforts mainly involve pruning and compression the weights of layers to reduce these costs, and use randomly initializing weights to fine-tune the pruned model. However, these approaches always lose important weights, resulting in the compressed model performing that is even worse than the original model. To address this problem, we propose a novel method replaced the traditional fine-tuning method with the knowledge distillation algorithm in this paper. Meanwhile, With the Resnet152 model, our method obtained the accuracy of 73.83% on CIFAR100 data and 22x compression, respectively, ResNet110 SVHN achieve 49x compression with 98.23% accuracy and all of which are preferable to the state-of-the-art.

Sie haben noch keine Lizenz? Dann Informieren Sie sich jetzt über unsere Produkte:

Springer Professional "Wirtschaft+Technik"

Online-Abonnement

Mit Springer Professional "Wirtschaft+Technik" erhalten Sie Zugriff auf:

  • über 102.000 Bücher
  • über 537 Zeitschriften

aus folgenden Fachgebieten:

  • Automobil + Motoren
  • Bauwesen + Immobilien
  • Business IT + Informatik
  • Elektrotechnik + Elektronik
  • Energie + Nachhaltigkeit
  • Finance + Banking
  • Management + Führung
  • Marketing + Vertrieb
  • Maschinenbau + Werkstoffe
  • Versicherung + Risiko

Jetzt Wissensvorsprung sichern!

Springer Professional "Technik"

Online-Abonnement

Mit Springer Professional "Technik" erhalten Sie Zugriff auf:

  • über 67.000 Bücher
  • über 390 Zeitschriften

aus folgenden Fachgebieten:

  • Automobil + Motoren
  • Bauwesen + Immobilien
  • Business IT + Informatik
  • Elektrotechnik + Elektronik
  • Energie + Nachhaltigkeit
  • Maschinenbau + Werkstoffe




 

Jetzt Wissensvorsprung sichern!

Springer Professional "Wirtschaft"

Online-Abonnement

Mit Springer Professional "Wirtschaft" erhalten Sie Zugriff auf:

  • über 67.000 Bücher
  • über 340 Zeitschriften

aus folgenden Fachgebieten:

  • Bauwesen + Immobilien
  • Business IT + Informatik
  • Finance + Banking
  • Management + Führung
  • Marketing + Vertrieb
  • Versicherung + Risiko




Jetzt Wissensvorsprung sichern!

Literatur
1.
Zurück zum Zitat Chollet, F.: Xception: deep learning with depthwise separable convolutions. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 1251–1258 (2017) Chollet, F.: Xception: deep learning with depthwise separable convolutions. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 1251–1258 (2017)
2.
Zurück zum Zitat Courbariaux, M., Hubara, I., Soudry, D., El-Yaniv, R., Bengio, Y.: Binarized neural networks: Training deep neural networks with weights and activations constrained to +1 or \(-\)1. arXiv preprint arXiv:1602.02830 (2016) Courbariaux, M., Hubara, I., Soudry, D., El-Yaniv, R., Bengio, Y.: Binarized neural networks: Training deep neural networks with weights and activations constrained to +1 or \(-\)1. arXiv preprint arXiv:​1602.​02830 (2016)
3.
Zurück zum Zitat Denton, E.L., Zaremba, W., Bruna, J., LeCun, Y., Fergus, R.: Exploiting linear structure within convolutional networks for efficient evaluation. In: Advances in Neural Information Processing Systems, pp. 1269–1277 (2014) Denton, E.L., Zaremba, W., Bruna, J., LeCun, Y., Fergus, R.: Exploiting linear structure within convolutional networks for efficient evaluation. In: Advances in Neural Information Processing Systems, pp. 1269–1277 (2014)
4.
Zurück zum Zitat Guo, Y., Yao, A., Chen, Y.: Dynamic network surgery for efficient DNNs. In: Advances in Neural Information Processing Systems, pp. 1379–1387 (2016) Guo, Y., Yao, A., Chen, Y.: Dynamic network surgery for efficient DNNs. In: Advances in Neural Information Processing Systems, pp. 1379–1387 (2016)
7.
Zurück zum Zitat Howard, A.G., et al.: Mobilenets: Efficient convolutional neural networks for mobile vision applications. arXiv preprint arXiv:1704.04861 (2017) Howard, A.G., et al.: Mobilenets: Efficient convolutional neural networks for mobile vision applications. arXiv preprint arXiv:​1704.​04861 (2017)
9.
Zurück zum Zitat Iandola, F.N., Han, S., Moskewicz, M.W., Ashraf, K., Dally, W.J., Keutzer, K.: Squeezenet: Alexnet-level accuracy with 50x fewer parameters and \({<}\)0.5 mb model size. arXiv preprint arXiv:1602.07360 (2016) Iandola, F.N., Han, S., Moskewicz, M.W., Ashraf, K., Dally, W.J., Keutzer, K.: Squeezenet: Alexnet-level accuracy with 50x fewer parameters and \({<}\)0.5 mb model size. arXiv preprint arXiv:​1602.​07360 (2016)
10.
Zurück zum Zitat Jacob, B., et al.: Quantization and training of neural networks for efficient integer-arithmetic-only inference. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 2704–2713 (2018) Jacob, B., et al.: Quantization and training of neural networks for efficient integer-arithmetic-only inference. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 2704–2713 (2018)
11.
Zurück zum Zitat Lan, X., Zhu, X., Gong, S.: Knowledge distillation by on-the-fly native ensemble. In: Proceedings of the 32nd International Conference on Neural Information Processing Systems, pp. 7528–7538. Curran Associates Inc. (2018) Lan, X., Zhu, X., Gong, S.: Knowledge distillation by on-the-fly native ensemble. In: Proceedings of the 32nd International Conference on Neural Information Processing Systems, pp. 7528–7538. Curran Associates Inc. (2018)
12.
Zurück zum Zitat Li, H., Kadav, A., Durdanovic, I., Samet, H., Graf, H.P.: Pruning filters for efficient convnets. arXiv preprint arXiv:1608.08710 (2016) Li, H., Kadav, A., Durdanovic, I., Samet, H., Graf, H.P.: Pruning filters for efficient convnets. arXiv preprint arXiv:​1608.​08710 (2016)
13.
Zurück zum Zitat Zagoruyko, S., Komodakis, N.: Paying more attention to attention: Improving the performance of convolutional neural networks via attention transfer. arXiv preprint arXiv:1612.03928 (2016) Zagoruyko, S., Komodakis, N.: Paying more attention to attention: Improving the performance of convolutional neural networks via attention transfer. arXiv preprint arXiv:​1612.​03928 (2016)
14.
Zurück zum Zitat Zhang, X., Zou, J., Ming, X., He, K., Sun, J.: Efficient and accurate approximations of nonlinear convolutional networks. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 1984–1992 (2015) Zhang, X., Zou, J., Ming, X., He, K., Sun, J.: Efficient and accurate approximations of nonlinear convolutional networks. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 1984–1992 (2015)
Metadaten
Titel
Knowledge Distillation Based on Pruned Model
verfasst von
Cailing Liu
Hongyi Zhang
Deyi Chen
Copyright-Jahr
2020
Verlag
Springer Singapore
DOI
https://doi.org/10.1007/978-981-15-2777-7_49