Abstract
Recently, alpha matting has received a lot of attention because of its usefulness in mobile applications such as selfies. Therefore, there has been a demand for a lightweight alpha matting model due to the limited computational resources of commercial portable devices. To this end, we suggest a distillation-based channel pruning method for the alpha matting networks. In the pruning step, we remove channels of a student network having fewer impacts on mimicking the knowledge of a teacher network. Then, the pruned lightweight student network is trained by the same distillation loss. A lightweight alpha matting model from the proposed method outperforms existing lightweight methods. To show superiority of our algorithm, we provide various quantitative and qualitative experiments with in-depth analyses. Furthermore, we demonstrate the versatility of the proposed distillation-based channel pruning method by applying it to semantic segmentation.
Project page is at https://github.com/DongGeun-Yoon/DCP.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Similar content being viewed by others
References
Aksoy, Y., Aydin, T.O., Pollefeys, M.: Designing effective inter-pixel information flow for natural image matting. In: Proceedings of Computer Vision and Pattern Recognition (CVPR) (2017)
Cai, S., et al.: Disentangled image matting. In: Proceedings of International Conference on Computer Vision (ICCV) (2019)
Changpinyo, S., Sandler, M., Zhmoginov, A.: The power of sparsity in convolutional neural networks. Ar**v abs/1702.06257 (2017)
Chen, Q., Li, D., Tang, C.K.: KNN matting. In: Proceedings of Computer Vision and Pattern Recognition (CVPR) (2012)
Chen, X., Zou, D., Zhou, S.Z., Zhao, Q., Tan, P.: Image matting with local and nonlocal smooth priors. In: Proceedings of Computer Vision and Pattern Recognition (CVPR) (2013)
Chen, X., Wang, Y., Zhang, Y., Du, P., Xu, C., Xu, C.: Multi-task pruning for semantic segmentation networks. Ar**v abs/2007.08386 (2020)
Cho, D., Kim, S., Tai, Y.-W.: Consistent matting for light field images. In: Fleet, D., Pajdla, T., Schiele, B., Tuytelaars, T. (eds.) ECCV 2014. LNCS, vol. 8692, pp. 90–104. Springer, Cham (2014). https://doi.org/10.1007/978-3-319-10593-2_7
Cho, D., Kim, S., Tai, Y.W., Kweon, I.S.: Automatic trimap generation and consistent matting for light-field images. IEEE Trans. Pattern Anal. Mach. Intell. (TPAMI) 39(8), 1504–1517 (2016)
Cho, D., Tai, Y.W., Kweon, I.S.: Deep convolutional neural network for natural image matting using initial alpha mattes. IEEE Trans. Image Process. (TIP) 28(3), 1054–1067 (2018)
Cho, D., Tai, Y.-W., Kweon, I.: Natural image matting using deep convolutional neural networks. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016. LNCS, vol. 9906, pp. 626–643. Springer, Cham (2016). https://doi.org/10.1007/978-3-319-46475-6_39
Choi, I., Lee, M., Tai, Y.-W.: Video matting using multi-frame nonlocal matting laplacian. In: Fitzgibbon, A., Lazebnik, S., Perona, P., Sato, Y., Schmid, C. (eds.) ECCV 2012. LNCS, vol. 7577, pp. 540–553. Springer, Heidelberg (2012). https://doi.org/10.1007/978-3-642-33783-3_39
Chuang, Y.Y., Curless, B., Salesin, D.H., Szeliski, R.: A Bayesian approach to digital matting. In: Proceedings of Computer Vision and Pattern Recognition (CVPR) (2001)
Everingham, M., Eslami, S.M.A., Gool, L.V., Williams, C.K.I., Winn, J.M., Zisserman, A.: The pascal visual object classes challenge: a retrospective. Int. J. Comput. Vision 111, 98–136 (2014)
Frankle, J., Carbin, M.: The lottery ticket hypothesis: finding sparse, trainable neural networks. In: International Conference on Learning Representations (2019)
Gao, X., Zhao, Y., Łukasz Dudziak, Mullins, R., zhong Xu, C.: Dynamic channel pruning: feature boosting and suppression. In: International Conference on Learning Representations (2019)
Gastal, E.S.L., Oliveira, M.M.: Shared sampling for real-time alpha matting. In: Eurographics (2010)
Ge, S., Zhao, S., Li, C., Li, J.: Low-resolution face recognition in the wild via selective knowledge distillation. IEEE Trans. Image Process. (TIP) 28(4), 2051–2062 (2019)
Han, S., Pool, J., Tran, J., Dally, W.J.: Learning both weights and connections for efficient neural networks. In: Proceedings of Neural Information Processing Systems (NeurIPS), pp. 1135–1143 (2015)
He, K., Rhemann, C., Rother, C., Tang, X., Sun, J.: A global sampling method for alpha matting. In: Proceedings of Computer Vision and Pattern Recognition (CVPR) (2011)
He, K., Sun, J., Tang, X.: Fast matting using large kernel matting laplacian matrices. In: Proceedings of Computer Vision and Pattern Recognition (CVPR) (2010)
He, W., Wu, M., Liang, M., Lam, S.K.: CAP: context-aware pruning for semantic segmentation. In: Proceedings of Winter Conference on Applications of Computer Vision (WACV), pp. 960–969 (2021)
Heo, B., Kim, J., Yun, S., Park, H., Kwak, N., Choi, J.Y.: A comprehensive overhaul of feature distillation. In: Proceedings of International Conference on Computer Vision (ICCV) (2019)
Hinton, G., Vinyals, O., Dean, J.: Distilling the knowledge in a neural network. In: Proceedings of Neural Information Processing Systems Workshops (NeurIPSW) (2015)
Huang, Z., Wang, N.: Like what you like: knowledge distill via neuron selectivity transfer. Ar**v abs/1707.01219 (2017)
Karacan, L., Erdem, A., Erdem, E.: Image matting with kl-divergence based sparse sampling. In: Proceedings of International Conference on Computer Vision (ICCV) (2015)
Ko, S., Park, J., Chae, B., Cho, D.: Learning lightweight low-light enhancement network using pseudo well-exposed images. IEEE Signal Process. Lett. (SPL) 29, 289–293 (2022)
Lee, P., Wu, Y.: Nonlocal matting. In: Proceedings of Computer Vision and Pattern Recognition (CVPR) (2011)
Levin, A., Lischinski, D., Weiss, Y.: A closed-form solution to natural image matting. IEEE Trans. Pattern Anal. Mach. Intell. (TPAMI) 30(2), 0162–8828 (2008)
Li, H., Kadav, A., Durdanovic, I., Samet, H., Graf, H.P.: Pruning filters for efficient convnets. In: International Conference on Learning Representation (ICLR) (2017)
Li, Y., Lu, H.: Natural image matting via guided contextual attention. In: Association for the Advancement of Artificial Intelligence (AAAI) (2020)
Liu, Z., Li, J., Shen, Z., Huang, G., Yan, S., Zhang, C.: Learning efficient convolutional networks through network slimming. In: Proceedings of International Conference on Computer Vision (ICCV), pp. 2736–2744 (2017)
Liu, Z., Sun, M., Zhou, T., Huang, G., Darrell, T.: Rethinking the value of network pruning. In: ICLR (2019)
Long, J., Shelhamer, E., Darrell, T.: Fully convolutional networks for semantic segmentation. In: Proceedings of Computer Vision and Pattern Recognition (CVPR), pp. 3431–3440 (2015)
Lu, H., Dai, Y., Shen, C., Xu, S.: Indices matter: learning to index for deep image matting. In: Proceedings of International Conference on Computer Vision (ICCV) (2019)
Lutz, S., Amplianitis, K., Smolic, A.: AlphaGAN: generative adversarial networks for natural image matting. In: British Machine Vision Conference (BMVC) (2018)
Molchanov, D., Ashukha, A., Vetrov, D.: Variational dropout sparsifies deep neural networks. In: Proceedings of International Conference on Machine Learning (ICML), pp. 2498–2507 (2017)
Qiao, Y., et al.: Attention-guided hierarchical structure aggregation for image matting. In: Proceedings of Computer Vision and Pattern Recognition (CVPR) (2020)
Ronneberger, O., Fischer, P., Brox, T.: U-net: convolutional networks for biomedical image segmentation. In: Navab, N., Hornegger, J., Wells, W.M., Frangi, A.F. (eds.) MICCAI 2015. LNCS, vol. 9351, pp. 234–241. Springer, Cham (2015). https://doi.org/10.1007/978-3-319-24574-4_28
Sandler, M., Howard, A., Zhu, M., Zhmoginov, A., Chen, L.C.: MobileNetv 2: Inverted residuals and linear bottlenecks. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2018)
Shahrian, E., Rajan, D., Price, B., Cohen, S.: Improving image matting using comprehensive sampling sets. In: Proceedings of Computer Vision and Pattern Recognition (CVPR) (2013)
Shahrian, E., Rajan, D.: Weighted color and texture sample selection for image matting. In: Proceedings of Computer Vision and Pattern Recognition (CVPR) (2012)
Shen, X., Tao, X., Gao, H., Zhou, C., Jia, J.: Deep automatic portrait matting. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016. LNCS, vol. 9905, pp. 92–107. Springer, Cham (2016). https://doi.org/10.1007/978-3-319-46448-0_6
Sun, J., Jia, J., Tang, C.K., Shum, H.Y.: Poisson matting. ACM Trans. Graph. (ToG) 23(3), 315–321 (2004)
Sun, Y., Tang, C.K., Tai, Y.W.: Semantic image matting. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 11120–11129 (2021)
Tanaka, H., Kunin, D., Yamins, D.L., Ganguli, S.: Pruning neural networks without any data by iteratively conserving synaptic flow. In: Larochelle, H., Ranzato, M., Hadsell, R., Balcan, M.F., Lin, H. (eds.) Advances in Neural Information Processing Systems, vol. 33, pp. 6377–6389. Curran Associates, Inc. (2020)
Tang, J., Aksoy, Y., Oztireli, C., Gross, M., Aydin, T.O.: Learning-based sampling for natural image matting. In: Proceedings of Computer Vision and Pattern Recognition (CVPR) (2019)
Tung, F., Mori, G.: Similarity-preserving knowledge distillation. In: Proceedings of International Conference on Computer Vision (ICCV) (2019)
Wang, J., Cohen, M.F.: Optimized color sampling for robust matting. In: Proceedings of Computer Vision and Pattern Recognition (CVPR) (2007)
Wen, W., Wu, C., Wang, Y., Chen, Y., Li, H.: Learning structured sparsity in deep neural networks. In: Proceedings of Neural Information Processing Systems (NeurIPS) (2016)
Xu, N., Price, B.L., Cohen, S., Huang, T.S.: Deep image matting. In: Proceedings of Computer Vision and Pattern Recognition (CVPR) (2017)
Yim, J., Joo, D., Bae, J., Kim, J.: A gift from knowledge distillation: Fast optimization, network minimization and transfer learning. In: Proceedings of Computer Vision and Pattern Recognition (CVPR) (2017)
Yoon, D., Park, J., Cho, D.: Lightweight deep CNN for natural image matting via similarity-preserving knowledge distillation. IEEE Signal Process. Lett. 27, 2139–2143 (2020)
Yu, Q., et al.: Mask guided matting via progressive refinement network. In: Proceedings of Computer Vision and Pattern Recognition (CVPR), pp. 1154–1163 (2021)
Zhao, H., Shi, J., Qi, X., Wang, X., Jia, J.: Pyramid scene parsing network. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2017)
Zheng, Y., Kambhamettu, C.: Learning based digital matting. In: Proceedings of International Conference on Computer Vision (ICCV) (2009)
Acknowledgements
This work was partly supported by Institute of Information & communications Technology Planning & Evaluation (IITP) grant funded by the Korea government (MSIT) (No. RS-2022-00155857, Artificial Intelligence Convergence Innovation Human Resources Development (Chungnam National University)) and the National Research Foundation of Korea (NRF) grant funded by the Korea government (MSIT, No. 2021R1A4A1032580 and No. 2022R1C1C1009334).
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
© 2023 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Yoon, D., Park, J., Cho, D. (2023). Lightweight Alpha Matting Network Using Distillation-Based Channel Pruning. In: Wang, L., Gall, J., Chin, TJ., Sato, I., Chellappa, R. (eds) Computer Vision – ACCV 2022. ACCV 2022. Lecture Notes in Computer Science, vol 13843. Springer, Cham. https://doi.org/10.1007/978-3-031-26313-2_7
Download citation
DOI: https://doi.org/10.1007/978-3-031-26313-2_7
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-26312-5
Online ISBN: 978-3-031-26313-2
eBook Packages: Computer ScienceComputer Science (R0)