Abstract
Nowadays, with the rapid development of mobile communication, big data and artificial intelligence technology, the optimization of face detection technology has become an important research direction in all fields. However, the existing face detection technology is not good enough to meet the requirements of all computing scenarios, and there are series of shortcomings, such as too many network parameters, longtime training and low detection success rate. In this paper, Widerface dataset published by the Chinese University of Hong Kong is used to study RetinaFace model and its effect. And the inverted residual structure is introduced by updating the main neural network, by loading which we work out RemFace at last. While adjusting the network structure, the neural degeneration phenomenon existing in previous studies is optimized, and the prediction effect is improved. Compared with MobileNetV1, RemFace has higher prediction accuracy and fewer model parameters, thus reducing computational overhead and enhancing real-time prediction. Finally, the paper summarizes the experimental results, and makes a simple prospect for the future research direction.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Krizhevsky, A., Sutskever, I., Hinton, G.: ImageNet classification with deep convolutional neural networks. In: Advances in Neural Information Processing Systems, pp. 1106–1114 (2012)
Simonyan, K., Zisserman, A.: Very deep convolutional networks for large-scale image recognition. Computer Science, pp. 1–9 (2014)
Szegedy, C., Liu, W., Jia, Y., et al.: Going deeper with convolutions. IEEE Computer Society (2014)
He, K., Zhang, X., Ren, S., et al.: Deep residual learning for image recognition. In: IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 770–778 (2016)
Nikbakht, S., Anitescu, C., Rabczuk, T.: Optimizing the neural network hyperparameters utilizing genetic algorithm. J. Zhejiang Univ. Sci. A 22, 407–426 (2021)
Zheng, M., Tang, W., Zhao, X.: Hyperparameter optimization of neural network-driven spatial models accelerated using cyber-enabled high-performance computing. Int. J. Geogr. Inf. Sci. 33(2), 314–345 (2018)
Snoek, J., Rippel, O., Swersky, K., Kiros, R.: Scalable Bayesian optimization using deep neural networks, pp. 2171–2180 (2015)
Hur, C., Kang, S.: Entropy-based pruning method for convolutional neural networks. J. Supercomput. 75(6), 2950–2963 (2018). https://doi.org/10.1007/s11227-018-2684-z
Xie, G.: Redundancy-aware pruning of convolutional neural networks. Neural Comput. 32(12), 2532–2556 (2020)
Bao, R.X., Yuan, X., Chen, Z.K., Ma, R.X.: Cross-entropy pruning for compressing con-volutional neural networks. Neural Comput. 30(11), 3128–3149 (2018)
Ruan, X.: EDP: an efficient decomposition and pruning scheme for convolutional neural network compression. IEEE Trans. Neural Netw. Learn. Syst. 32, 4499–4513 (2021)
Wang, Z.Y., Xie, X.M., Shi, G.M.: RFPruning: a retraining-free pruning method for accelerating convolutional neural networks. Appl. Soft Comput. 113, 107860 (2021)
Ashouri, A.H., Abdelrahman, T.S., Remedios, A.D.: Retraining-free methods for fast on-the-fly pruning of convolutional neural networks. Neurocomputing 370, 56–69 (2019)
Ahmed, K., Torresani, L.: Connectivity learning in multi-branch networks. arXiv:1709.09582. (2017)
Veniat, T., Denoyer, L.: Learning time efficient deep architectures with budgeted super networks. arXiv:1706.00046 (2017)
Zhang, X., Zhou, X., Lin, M., Sun, J.: ShuffleNet: an extremely efficient convolutional neural network for mobile devices. arXiv:1707.01083 (2017)
Changpinyo, S., Sandler, M., Zhmoginov, A.: The power of sparsity in convolutional neural networks. arXiv:1702.06257 (2017)
Wang, M., Liu, B., Foroosh, H.: Design of efficient convolutional layers using single intra-channel convolution, topological subdivisioning and spatial ‘bottleneck’ structure. arXiv:1608.04337 (2016)
Deng, J., Guo, J., Zhou, Y., et al: RetinaFace: single-stage dense face localisation in the wild. arXiv:1905.00641 (2020)
Lin, T.Y., Dollar, P., Girshick, R.: Feature pyramid networks for object detection. In: IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2017)
Deng, J., Guo, J., Xue, N., Zafeiriou, S.: ArcFace: additive angular margin loss for deep face recognition. In: CVPR (2019)
Najibi, M., Samangouei, P., Chellappa, R., Davis, L.S.: SSH: single stage headless face detector. In: ICCV (2017)
Howard, A.G., Zhu, M., Chen, B.: MobileNets: efficient convolutional neural networks for mobile vision applications. IEEE Access (2017)
Shuai, G.: Deep learning based object detection technology research under android mobile platform. Master’s theses, XiDian University, Xi’An (2018)
Sandler, M., Howard, A., Zhu, M., et al.: MobileNetv2: inverted residuals and linear bottlenecks. In: IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 4510–4520 (2018)
Neubeck, A., Gool, L.J.V.: Efficient non-maximum suppression. In: 18th International Conference on Pattern Recognition (ICPR 2006), pp. 20–24 (2006)
Yang, S., Luo, P., Loy, C.C., et al.: WIDER FACE: a face detection benchmark. In: IEEE Conference on Computer Vision & Pattern Recognition (2016)
Niu, Z.D., Qin, T., Li, H.D., Chen, J.J.: Improved algorithm of retinaface for natural scene mask wear detection. Comput. Eng. Appl. 56, 1–7 (2020)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2022 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Wang, Z., Wu, T., Wang, Y., Li, Y. (2022). Remface: Study on Mini-sized Mobilenetv2 and Retinaface. In: Sun, X., Zhang, X., Xia, Z., Bertino, E. (eds) Artificial Intelligence and Security. ICAIS 2022. Lecture Notes in Computer Science, vol 13339. Springer, Cham. https://doi.org/10.1007/978-3-031-06788-4_1
Download citation
DOI: https://doi.org/10.1007/978-3-031-06788-4_1
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-06787-7
Online ISBN: 978-3-031-06788-4
eBook Packages: Computer ScienceComputer Science (R0)