Abstract
Video style transfer techniques inspire many exciting applications on mobile devices. However, their efficiency and stability are still far from satisfactory. To boost the transfer stability across frames, optical flow is widely adopted, despite its high computational complexity, e.g. occupying over 97% inference time. This paper proposes to learn a lightweight video style transfer network via knowledge distillation paradigm. We adopt two teacher networks, one of which takes optical flow during inference while the other does not. The output difference between these two teacher networks highlights the improvements made by optical flow, which is then adopted to distill the target student network. Furthermore, a low-rank distillation loss is employed to stabilize the output of student network by mimicking the rank of input videos. Extensive experiments demonstrate that our student network without an optical flow module is still able to generate stable video and runs much faster than the teacher network.
X. Chen and Y. Zhang—Equal Contribution.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Butler, D.J., Wulff, J., Stanley, G.B., Black, M.J.: A naturalistic open source movie for optical flow evaluation. In: Fitzgibbon, A., Lazebnik, S., Perona, P., Sato, Y., Schmid, C. (eds.) ECCV 2012. LNCS, vol. 7577, pp. 611–625. Springer, Heidelberg (2012). https://doi.org/10.1007/978-3-642-33783-3_44
Chen, D., Liao, J., Yuan, L., Yu, N., Hua, G.: Coherent online video style transfer. In: ICCV, pp. 1105–1114 (2017)
Chen, D., Yuan, L., Liao, J., Yu, N., Hua, G.: Stylebank: an explicit representation for neural image style transfer. In: CVPR, pp. 1897–1906 (2017)
Chen, G., Choi, W., Yu, X., Han, T., Chandraker, M.: Learning efficient object detection models with knowledge distillation. In: NIPS, pp. 742–751 (2017)
Chen, H., Wang, Y., Xu, C., Xu, C., Tao, D.: Learning student networks via feature embedding. TNNLS (2020)
Chen, H., et al.: Data-free learning of student networks. In: ICCV (2019)
Dumoulin, V., Shlens, J., Kudlur, M.: A learned representation for artistic style. In: ICLR (2017)
Gao, C., Gu, D., Zhang, F., Yu, Y.: ReCoNet: real-time coherent video style transfer network. In: Jawahar, C.V., Li, H., Mori, G., Schindler, K. (eds.) ACCV 2018. LNCS, vol. 11366, pp. 637–653. Springer, Cham (2019). https://doi.org/10.1007/978-3-030-20876-9_40
Gao, W., Li, Y., Yin, Y., Yang, M.H.: Fast video multi-style transfer. In: WACV, pp. 3222–3230 (2020)
Gatys, L.A., Ecker, A.S., Bethge, M.: A neural algorithm of artistic style. arXiv preprint arXiv:1508.06576 (2015)
Gatys, L.A., Ecker, A.S., Bethge, M.: Image style transfer using convolutional neural networks. In: CVPR, pp. 2414–2423 (2016)
Gong, X., Chang, S., Jiang, Y., Wang, Z.: Autogan: neural architecture search for generative adversarial networks. In: ICCV, pp. 3224–3234 (2019)
Gupta, A., Johnson, J., Alahi, A., Fei-Fei, L.: Characterizing and improving stability in neural style transfer. In: ICCV, pp. 4067–4076 (2017)
He, T., Shen, C., Tian, Z., Gong, D., Sun, C., Yan, Y.: Knowledge adaptation for efficient semantic segmentation. In: CVPR, pp. 578–587 (2019)
He, Y., Zhang, X., Sun, J.: Channel pruning for accelerating very deep neural networks. In: ICCV (2017)
Heo, B., Kim, J., Yun, S., Park, H., Kwak, N., Choi, J.Y.: A comprehensive overhaul of feature distillation. In: ICCV, pp. 1921–1930 (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)
Huang, H., et al.: Real-time neural style transfer for videos. In: CVPR, pp. 783–791 (2017)
Huang, Z., Wang, N.: Like what you like: Knowledge distill via neuron selectivity transfer. arXiv preprint arXiv:1707.01219 (2017)
Jiao, J., Wei, Y., Jie, Z., Shi, H., Lau, R.W., Huang, T.S.: Geometry-aware distillation for indoor semantic segmentation. In: CVPR, pp. 2869–2878 (2019)
Johnson, J., Alahi, A., Fei-Fei, L.: Perceptual losses for real-time style transfer and super-resolution. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016. LNCS, vol. 9906, pp. 694–711. Springer, Cham (2016). https://doi.org/10.1007/978-3-319-46475-6_43
Li, Q., Jin, S., Yan, J.: Mimicking very efficient network for object detection. In: CVPR, pp. 6356–6364 (2017)
Li, Y., Fang, C., Yang, J., Wang, Z., Lu, X., Yang, M.H.: Universal style transfer via feature transforms. In: NIPS, pp. 386–396 (2017)
Liao, J., Yao, Y., Yuan, L., Hua, G., Kang, S.B.: Visual attribute transfer through deep image analogy. ACM Trans. Graph. (TOG) 36(4), 1–15 (2017)
Liu, Y., Chen, K., Liu, C., Qin, Z., Luo, Z., Wang, J.: Structured knowledge distillation for semantic segmentation. In: CVPR, pp. 2604–2613 (2019)
Liu, Z., Wu, B., Luo, W., Yang, X., Liu, W., Cheng, K.-T.: Bi-real net: enhancing the performance of 1-Bit CNNs with improved representational capability and advanced training algorithm. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) ECCV 2018. LNCS, vol. 11219, pp. 747–763. Springer, Cham (2018). https://doi.org/10.1007/978-3-030-01267-0_44
Liu, Z., Sun, M., Zhou, T., Huang, G., Darrell, T.: Rethinking the value of network pruning. In: ICLR (2019)
Lu, M., Zhao, H., Yao, A., Chen, Y., Xu, F., Zhang, L.: A closed-form solution to universal style transfer. In: ICCV, October 2019
Lu, M., Zhao, H., Yao, A., Xu, F., Chen, Y., Zhang, L.: Decoder network over lightweight reconstructed feature for fast semantic style transfer. In: ICCV, pp. 2469–2477 (2017)
Marszałek, M., Laptev, I., Schmid, C.: Actions in context. In: CVPR, pp. 2929–2936. IEEE Computer Society (2009)
Romero, A., Ballas, N., Kahou, S.E., Chassang, A., Gatta, C., Bengio, Y.: Fitnets: hints for thin deep nets. In: ICLR (2015)
Ruder, M., Dosovitskiy, A., Brox, T.: Artistic style transfer for videos. In: Rosenhahn, B., Andres, B. (eds.) GCPR 2016. LNCS, vol. 9796, pp. 26–36. Springer, Cham (2016). https://doi.org/10.1007/978-3-319-45886-1_3
Ruder, M., Dosovitskiy, A., Brox, T.: Artistic style transfer for videos and spherical images. IJCV 126(11), 1199–1219 (2018)
Saputra, M.R.U., de Gusmao, P.P., Almalioglu, Y., Markham, A., Trigoni, N.: Distilling knowledge from a deep pose regressor network. In: ICCV (2019)
Shen, M., Han, K., Xu, C., Wang, Y.: Searching for accurate binary neural architectures. In: ICCV Neural Architects Workshop (2019)
Shu, H., et al.: Co-evolutionary compression for unpaired image translation. In: ICCV, pp. 3235–3244 (2019)
Wang, C., Kong, C., Lucey, S.: Distill knowledge from NRSfM for weakly supervised 3D pose learning. In: ICCV, pp. 743–752 (2019)
Wang, W., Xu, J., Zhang, L., Wang, Y., Liu, J.: Consistent video style transfer via compound regularization. In: AAAI, pp. 12233–12240 (2020)
Wang, Y., Xu, C., Xu, C., Tao, D.: Adversarial learning of portable student networks. In: AAAI (2018)
Wei, Y., Pan, X., Qin, H., Ouyang, W., Yan, J.: Quantization mimic: towards very tiny CNN for object detection. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) ECCV 2018. LNCS, vol. 11212, pp. 274–290. Springer, Cham (2018). https://doi.org/10.1007/978-3-030-01237-3_17
Yang, Z., et al.: Cars: continuous evolution for efficient neural architecture search. In: CVPR, pp. 1829–1838 (2020)
Yim, J., Joo, D., Bae, J., Kim, J.: A gift from knowledge distillation: fast optimization, network minimization and transfer learning. In: CVPR, pp. 4133–4141 (2017)
Zagoruyko, S., Komodakis, N.: Paying more attention to attention: improving the performance of convolutional neural networks via attention transfer. In: ICLR (2017)
Zhou, S., Wu, Y., Ni, Z., Zhou, X., Wen, H., Zou, Y.: DoReFa-Net: Training low bitwidth convolutional neural networks with low bitwidth gradients. arXiv preprint arXiv:1606.06160 (2016)
Acknowledgments
We thank anonymous reviewers for their helpful comments. Chang Xu was supported by the Australian Research Council under Project DE180101438.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
1 Electronic supplementary material
Below is the link to the electronic supplementary material.
Rights and permissions
Copyright information
© 2020 Springer Nature Switzerland AG
About this paper
Cite this paper
Chen, X., Zhang, Y., Wang, Y., Shu, H., Xu, C., Xu, C. (2020). Optical Flow Distillation: Towards Efficient and Stable Video Style Transfer. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, JM. (eds) Computer Vision – ECCV 2020. ECCV 2020. Lecture Notes in Computer Science(), vol 12351. Springer, Cham. https://doi.org/10.1007/978-3-030-58539-6_37
Download citation
DOI: https://doi.org/10.1007/978-3-030-58539-6_37
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-58538-9
Online ISBN: 978-3-030-58539-6
eBook Packages: Computer ScienceComputer Science (R0)