Abstract
Knowledge distillation has become increasingly important in model compression. It boosts the performance of a miniaturized student network with the supervision of the output distribution and feature maps from a sophisticated teacher network. Some recent works introduce multi-teacher distillation to provide more supervision to the student network. However, the effectiveness of multi-teacher distillation methods are accompanied by costly computation resources. To tackle with both the efficiency and the effectiveness of knowledge distillation, we introduce the feature aggregation to imitate the multi-teacher distillation in the single-teacher distillation framework by extracting informative supervision from multiple teacher feature maps. Specifically, we introduce DFA, a two-stage Differentiable Feature Aggregation search method that motivated by DARTS in neural architecture search, to efficiently find the aggregations. In the first stage, DFA formulates the searching problem as a bi-level optimization and leverages a novel bridge loss, which consists of a student-to-teacher path and a teacher-to-student path, to find appropriate feature aggregations. The two paths act as two players against each other, trying to optimize the unified architecture parameters to the opposite directions while guaranteeing both expressivity and learnability of the feature aggregation simultaneously. In the second stage, DFA performs knowledge distillation with the derived feature aggregation. Experimental results show that DFA outperforms existing distillation methods on CIFAR-100 and CINIC-10 datasets under various teacher-student settings, verifying the effectiveness and robustness of the design.
Y. Guan and P. Zhao: These authors contributed equally to this work.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Similar content being viewed by others
References
Bender, G., Kindermans, P.J., Zoph, B., Vasudevan, V., Le, Q.: Understanding and simplifying one-shot architecture search. In: ICML, pp. 550–559 (2018)
Bucilua, C., Caruana, R., Niculescu-Mizil, A.: Model compression. In: KDD, pp. 535–541. ACM (2006)
Cai, H., Yang, J., Zhang, W., Han, S., Yu, Y.: Path-level network transformation for efficient architecture search. In: International Conference on Machine Learning, pp. 678–687 (2018)
Cai, H., Zhu, L., Han, S.: ProxylessNAS: direct neural architecture search on target task and hardware. In: ICLR (2019)
Chen, X., Xie, L., Wu, J., Tian, Q.: Progressive differentiable architecture search: bridging the depth gap between search and evaluation. In: ICCV (2019)
Darlow, L.N., Crowley, E.J., Antoniou, A., Storkey, A.J.: CINIC-10 is not ImageNet or CIFAR-10. arXiv preprint arXiv:1810.03505 (2018)
Dong, X., Yang, Y.: Network pruning via transformable architecture search. In: Advances in Neural Information Processing Systems, pp. 759–770 (2019)
Dong, X., Yang, Y.: One-shot neural architecture search via self-evaluated template network. In: ICCV, pp. 3681–3690 (2019)
He, K., Zhang, X., Ren, S., Sun, J.: Delving deep into rectifiers: surpassing human-level performance on imagenet classification. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 1026–1034 (2015)
Heo, B., Kim, J., Yun, S., Park, H., Kwak, N., Choi, J.Y.: A comprehensive overhaul of feature distillation. In: ICCV, October 2019
Heo, B., Kim, J., Yun, S., Park, H., Kwak, N., Choi, J.Y.: A comprehensive overhaul of feature distillation. arXiv preprint arXiv:1904.01866 (2019)
Heo, B., Lee, M., Yun, S., Choi, J.Y.: Knowledge transfer via distillation of activation boundaries formed by hidden neurons. In: AAAI, vol. 33, pp. 3779–3787 (2019)
Hinton, G., Vinyals, O., Dean, J.: Distilling the knowledge in a neural network. arXiv preprint arXiv:1503.02531 (2015)
Hubara, I., Courbariaux, M., Soudry, D., El-Yaniv, R., Bengio, Y.: Binarized neural networks. In: Advances in Neural Information Processing Systems, pp. 4107–4115 (2016)
Kang, M., Mun, J., Han, B.: Towards oracle knowledge distillation with neural architecture search. arXiv preprint arXiv:1911.13019 (2019)
Kim, J., Park, S., Kwak, N.: Paraphrasing complex network: network compression via factor transfer. In: Advances in Neural Information Processing Systems, pp. 2760–2769 (2018)
Kingma, D.P., Ba, J.: Adam: a method for stochastic optimization. arXiv preprint arXiv:1412.6980 (2014)
Krizhevsky, A., Hinton, G., et al.: Learning multiple layers of features from tiny images (2009)
Leng, C., Dou, Z., Li, H., Zhu, S., Jin, R.: Extremely low bit neural network: squeeze the last bit out with ADMM. In: Thirty-Second AAAI Conference on Artificial Intelligence (2018)
Li, C., et al.: Blockwisely supervised neural architecture search with knowledge distillation. arXiv preprint arXiv:1911.13053 (2019)
Li, H., Kadav, A., Durdanovic, I., Samet, H., Graf, H.P.: Pruning filters for efficient convNets. arXiv preprint arXiv:1608.08710 (2016)
Li, W., Gong, S., Zhu, X.: Neural graph embedding for neural architecture search. In: AAAI (2020)
Lin, X., Zhao, C., Pan, W.: Towards accurate binary convolutional neural network. In: Advances in Neural Information Processing Systems, pp. 345–353 (2017)
Liu, H., Simonyan, K., Yang, Y.: DARTS: differentiable architecture search. In: ICLR (2019)
Ma, N., Zhang, X., Zheng, H.T., Sun, J.: ShuffleNet V2: Practical guidelines for efficient CNN architecture design. In: Proceedings of the European Conference on Computer Vision (ECCV), pp. 116–131 (2018)
Nayman, N., Noy, A., Ridnik, T., Friedman, I., Jin, R., Zelnik, L.: XNAS: neural architecture search with expert advice. In: Advances in Neural Information Processing Systems, pp. 1975–1985 (2019)
Pham, H., Guan, M., Zoph, B., Le, Q., Dean, J.: Efficient neural architecture search via parameter sharing. In: ICML, pp. 4092–4101 (2018)
Real, E., Aggarwal, A., Huang, Y., Le, Q.V.: Regularized evolution for image classifier architecture search. In: AAAI, vol. 33, pp. 4780–4789 (2019)
Real, E., et al.: Large-scale evolution of image classifiers. In: ICML, pp. 2902–2911 (2017)
Romero, A., Ballas, N., Kahou, S.E., Chassang, A., Gatta, C., Bengio, Y.: FitNets: hints for thin deep nets. arXiv preprint arXiv:1412.6550 (2014)
Srinivas, S., Fleuret, F.: Knowledge transfer with Jacobian matching. arXiv preprint arXiv:1803.00443 (2018)
Tan, M., et al.: MnasNet: platform-aware neural architecture search for mobile. In: CVPR, pp. 2820–2828 (2019)
Tung, F., Mori, G.: Similarity-preserving knowledge distillation. In: ICCV, pp. 1365–1374 (2019)
Wen, W., Wu, C., Wang, Y., Chen, Y., Li, H.: Learning structured sparsity in deep neural networks. In: Advances in Neural Information Processing Systems, pp. 2074–2082 (2016)
Xie, S., Zheng, H., Liu, C., Lin, L.: SNAS: stochastic neural architecture search. In: ICLR (2019)
Xu, Y., et al.: PC-DARTS: partial channel connections for memory-efficient differentiable architecture search. In: ICLR (2020)
You, S., Xu, C., Xu, C., Tao, D.: Learning from multiple teacher networks. In: KDD, pp. 1285–1294. ACM (2017)
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.: Wide residual networks. arXiv preprint arXiv:1605.07146 (2016)
Zela, A., Elsken, T., Saikia, T., Marrakchi, Y., Brox, T., Hutter, F.: Understanding and robustifying differentiable architecture search. In: ICLR (2020)
Zoph, B., Le, Q.V.: Neural architecture search with reinforcement learning. In: ICLR (2017)
Zoph, B., Vasudevan, V., Shlens, J., Le, Q.V.: Learning transferable architectures for scalable image recognition. In: CVPR, pp. 8697–8710 (2018)
Acknowledgment
This work is partially supported by National Key Research and Development Program No. 2017YFB0803302, Beijing Academy of Artificial Intelligence (BAAI), and NSFC 61632017.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2020 Springer Nature Switzerland AG
About this paper
Cite this paper
Guan, Y. et al. (2020). Differentiable Feature Aggregation Search for Knowledge Distillation. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, JM. (eds) Computer Vision – ECCV 2020. ECCV 2020. Lecture Notes in Computer Science(), vol 12362. Springer, Cham. https://doi.org/10.1007/978-3-030-58520-4_28
Download citation
DOI: https://doi.org/10.1007/978-3-030-58520-4_28
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-58519-8
Online ISBN: 978-3-030-58520-4
eBook Packages: Computer ScienceComputer Science (R0)