Abstract
In model compression, knowledge distillation is a popular algorithm, which trains a lightweight network (student) by learning the knowledge from a pre-trained complicated network (teacher). It is essential to acquire the training data that the teacher used since the knowledge is obtained by inputting training data to the teacher network. However, the data is often unavailable due to privacy problems or storage costs. Its lead exiting data-driven knowledge distillation methods is unable to apply to the real world. To solve these problems, in this paper, we propose a data-free knowledge distillation method called DFPU, which introduce positive-unlabeled (PU) learning. For training a compact neural network without data, a generator is introduced to generate pseudo data under the supervision of the teacher network. By feeding the generated data into the teacher network and student network, the attention features are extracted for knowledge transfer. The student network is promoted to produce more similar features to the teacher network by PU learning. Without any data, the efficient student network trained by DFPU contains only half parameters and calculations of the teacher network and achieves an accuracy similar to the teacher network.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
He, K., Zhang, X., Ren, S., Jian, S.: Deep residual learning for image recognition. In: 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2016)
Krizhevsky, A., Sutskever, I., Hinton, G.E.: ImageNet classification with deep convolutional neural networks. In: Advances in Neural Information Processing Systems, pp. 1097–1105 (2012)
LeCun, Y., Bottou, L., Bengio, Y., Haffner, P., et al.: Gradient-based learning applied to document recognition. Proc. IEEE 86(11), 2278–2324 (1998)
Girshick, R.B., Donahue, J., Darrell, T., Malik, J.: Rich feature hierarchies for accurate object detection and semantic segmentation. In: CVPR, pp. 580–587. IEEE Computer Society (2014)
Girshick, R.: Fast R-CNN. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 1440–1448 (2015)
Ren, S., He, K., Girshick, R., Sun, J.: Faster R-CNN: towards real-time object detection with region proposal networks. In: Advances in Neural Information Processing Systems, pp. 91–99 (2015)
Long, J., Shelhamer, E., Darrell, T.: Fully convolutional networks for semantic segmentation. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 3431–3440 (2015)
Yu, F., Koltun, V.: Multi-scale context aggregation by dilated convolutions. arXiv preprint arXiv:1511.07122 (2015)
Liu, Y., Chen, K., Liu, C., Qin, Z., Luo, Z., Wang, J.: Structured knowledge distillation for semantic segmentation. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 2604–2613 (2019)
Ba, L.J., Caruana, R.: Do deep nets really need to be deep? In: Advances in Neural Information Processing Systems, pp. 2654–2662 (2013)
Hinton, G., Vinyals, O., Dean, J.: Distilling the knowledge in a neural network. Comput. Sci. 14(7), 38–39 (2015)
Romero, A., Ballas, N., Kahou, S.E., Chassang, A., Gatta, C., Bengio, Y.: FitNets: hints for thin deep nets. Comput. Sci. (2014)
Bolukbasi, T., Wang, J., Dekel, O., Saligrama, V.: Adaptive neural networks for efficient inference. In: ICML, Series Proceedings of Machine Learning Research, vol. 70. PMLR, pp. 527–536 (2017)
Huang, Z., Wang, N.: Data-driven sparse structure selection for deep neural networks. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) ECCV 2018. LNCS, vol. 11220, pp. 317–334. Springer, Cham (2018). https://doi.org/10.1007/978-3-030-01270-0_19
Xu, S., Ren, X., Ma, S., Wang, H.: meProp: Sparsified back propagation for accelerated deep learning with reduced overfitting. In: ICML 2017 (2017)
Lopes, R.G., Fenu, S., Starner, T.: Data-free knowledge distillation for deep neural networks (2017)
Liu, Z., et al.: MetaPruning: meta learning for automatic neural network channel pruning. arXiv preprint arXiv:1903.10258 (2019)
Chen, H.: Data-free learning of student networks. In: Proceedings of the IEEE/CVF International Conference on Computer Vision, pp. 3514–3522 (2019)
Goodfellow, I.: Nips 2016 tutorial: generative adversarial networks. arXiv preprint arXiv:1701.00160 (2016)
Odena, A.: Semi-supervised learning with generative adversarial networks. arXiv preprint arXiv:1606.01583 (2016)
Krizhevsky, A., Hinton, G., et al.: Learning multiple layers of features from tiny images (2009)
Netzer, Y., Wang, T., Coates, A., Bissacco, A., Wu, B., Ng, A.Y.: Reading digits in natural images with unsupervised feature learning (2011)
Furlanello, T., Lipton, Z.C., Tschannen, M., Itti, L., Anandkumar, A.: Born again neural networks (2018)
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)
Yoo, J., Cho, M., Kim, T., Kang, U.: Knowledge extraction with no observable data (2019)
Nayak, G.K., Mopuri, K.R., Shaj, V., Radhakrishnan, V.B., Chakraborty, A.: Zero-shot knowledge distillation in deep networks. In: International Conference on Machine Learning. PMLR, pp. 4743–4751 (2019)
Wang, Z.: Data-free knowledge distillation with soft targeted transfer set synthesis. arXiv preprint arXiv:2104.04868 (2021)
Xu, Y., Xu, C., Xu, C., Tao, D.: Multi-positive and unlabeled learning. In: IJCAI, pp. 3182–3188 (2017)
Kiryo, R., Niu, G., Plessis, M.C.D., Sugiyama, M.: Positive-unlabeled learning with non-negative risk estimator. arXiv preprint arXiv:1703.00593 (2017)
Goodfellow, I., et al.: Generative adversarial nets. In: Advances in Neural Information Processing Systems, vol. 27 (2014)
Xi, C., Yan, D., Houthooft, R., Schulman, J., Abbeel, P.: InfoGAN: interpretable representation learning by information maximizing generative adversarial nets. In: Neural Information Processing Systems (NIPS) (2016)
Guo, T.: On positive-unlabeled classification in GAN. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 8385–8393 (2020)
Wang, F.: Residual attention network for image classification. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 3156–3164 (2017)
Hu, J., Shen, L., Sun, G.: Squeeze-and-excitation networks. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 7132–7141 (2018)
Simonyan, K., Zisserman, A.: Very deep convolutional networks for large-scale image recognition. Comput. Sci. (2014)
Yin, H.: Dreaming to distill: data-free knowledge transfer via DeepInversion. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 8715–8724 (2020)
Bottou, L.: Stochastic gradient descent tricks (2012)
Acknowledgement
This work was supported by the Mianyang Science and Technology Program 2020YFZJ016, SWUST Doctoral Foundation under Grant 19zx7102, 21zx7114, Sichuan Science and Technology Program under Grant 2020YFS0307.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2021 Springer Nature Switzerland AG
About this paper
Cite this paper
Tang, J., Yang, X., Cheng, X., Jiang, N., Yu, W., Zhang, P. (2021). Data-Free Knowledge Distillation with Positive-Unlabeled Learning. In: Mantoro, T., Lee, M., Ayu, M.A., Wong, K.W., Hidayanto, A.N. (eds) Neural Information Processing. ICONIP 2021. Lecture Notes in Computer Science(), vol 13109. Springer, Cham. https://doi.org/10.1007/978-3-030-92270-2_27
Download citation
DOI: https://doi.org/10.1007/978-3-030-92270-2_27
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-92269-6
Online ISBN: 978-3-030-92270-2
eBook Packages: Computer ScienceComputer Science (R0)