research-article

PruneFaceDet: Pruning Lightweight Face Detection Network by Sparsity Training

Authors:

Jinqiao WangAuthors Info & Claims

ICCPR '20: Proceedings of the 2020 9th International Conference on Computing and Pattern Recognition

Pages 181 - 186

https://doi.org/10.1145/3436369.3437415

Published: 11 January 2021 Publication History

Abstract

Face detection is the basic step of many face-analysis tasks. In practice, face detectors usually run on mobile devices with limited memory and computing resources. Therefore, it is important to keep the face detectors lightweight. To this end, current methods usually focus on directly design lightweight detectors. Nevertheless, the resource consumption of the lightweight detectors could be further suppressed. In this paper, we propose to apply the network pruning method to the lightweight face detection network, which can further reduce the face detector's parameters and floating point operations (FLOPs). To identify the channels of less importance, we perform the network training with sparsity regularization on channel scaling factors of each layer. Then, we remove the connections and the corresponding weights with the near-zero scaling factors after the sparsity training. We apply the proposed pruning pipeline on a state-of-the-art face detection method, EagleEye [5], and get a shrunken EalgeEye model which has a reduced number of computing operations and parameters. The shrunken model could achieve comparable accuracy as the unpruned model. By using the proposed method, the EagleEye face detector achieve 57.2% reduction of parameter size with 2% accuracy loss on WiderFace dataset.

References

[1]

Tsung-Yi Lin, Priya Goyal, Ross Girshick, Kaiming He, and Piotr Dollar, "Focal loss for dense object detection," in Proceedings of the IEEE international conference on computer vision, 2017, pp. 2980--2988.

[2]

Xu Tang, Daniel K Du, Zeqiang He, and Jingtuo Liu, "Pyramidbox: A context-assisted single shot face detector," in Proceedings of the European Conference on Computer Vision (ECCV), 2018, pp. 797--813.

[3]

Cheng Chi, Shifeng Zhang, Junliang Xing, Zhen Lei, Stan Z Li, and Xudong Zou, "Selective refinement network for high performance face detection," arXiv preprint arXiv:1809.02693, 2018.

[4]

Shifeng Zhang, Xiangyu Zhu, Zhen Lei, Hailin Shi, Xiaobo Wang, and Stan Z Li, "Faceboxes: A cpu real-time face detector with high accuracy," in 2017 IEEE International Joint Conference on Biometrics (IJCB). IEEE, 2017, pp. 1--9.

[5]

Xu Zhao, Xiaoqing Liang, Chaoyang Zhao, Ming Tang, and Jinqiao Wang, "Real-time multi-scale face detector on embedded devices," Sensors, vol. 19, no. 9, pp. 2158, 2019.

[6]

Itay Hubara, Matthieu Courbariaux, Daniel Soudry, Ran ElYaniv, and Yoshua Bengio, "Binarized neural networks: Training neural networks with weights and activations constrained to+ 1 or-1," arXiv preprint arXiv:1602.02830, 2016.

[7]

Mohammad Rastegari, Vicente Ordonez, Joseph Redmon, and Ali Farhadi, "Xnor-net: Imagenet classification using binary convolutional neural networks," in European conference on computer vision. Springer, 2016, pp. 525--542.

[8]

Jiaxiang Wu, Cong Leng, Yuhang Wang, Qinghao Hu, and Jian Cheng, "Quantized convolutional neural networks for mobile devices," in Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2016, pp. 4820--4828.

[9]

Benoit Jacob, Skirmantas Kligys, Bo Chen, Menglong Zhu, Matthew Tang, Andrew Howard, Hartwig Adam, and Dmitry Kalenichenko, "Quantization and training of neural networks for efficient integer-arithmetic-only inference," in Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2018, pp. 2704--2713.

[10]

Yi Wei, Xinyu Pan, Hongwei Qin, Wanli Ouyang, and Junjie Yan, "Quantization mimic: Towards very tiny cnn for object detection," in Proceedings of the European Conference on Computer Vision (ECCV), 2018, pp. 267--283.

[11]

Yang He, Ping Liu, Ziwei Wang, Zhilan Hu, and Yi Yang, "Filter pruning via geometric median for deep convolutional neural networks acceleration," in Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2019, pp. 4340--4349.

[12]

Zhuang Liu, Jianguo Li, Zhiqiang Shen, Gao Huang, Shoumeng Yan, and Changshui Zhang, "Learning efficient convolutional networks through network slimming," in Proceedings of the IEEE International Conference on Computer Vision, 2017, pp. 2736--2744.

[13]

Xuanyi Dong, Junshi Huang, Yi Yang, and Shuicheng Yan, "More is less: A more complicated network with less inference complexity," in Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2017, pp. 5840--5848.

[14]

Ruichi Yu, Ang Li, Chun-Fu Chen, Jui-Hsin Lai, Vlad I Morariu, Xintong Han, Mingfei Gao, Ching-Yung Lin, and Larry S Davis, "Nisp: Pruning networks using neuron importance score propagation," in Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2018, pp. 9194--9203.

[15]

Hao Li, Asim Kadav, Igor Durdanovic, Hanan Samet, and Hans Peter Graf, "Pruning filters for efficient convnets," arXiv preprint arXiv:1608.08710, 2016.

[16]

Hans Peter Graf, "Pruning filters for efficient convnets," arXiv preprint arXiv:1608.08710, 2016.

[17]

Yihui He, Xiangyu Zhang, and Jian Sun, "Channel pruning for accelerating very deep neural networks," in Proceedings of the IEEE International Conference on Computer Vision, 2017, pp. 1389--1397.

[18]

Byeongho Heo, Jeesoo Kim, Sangdoo Yun, Hyojin Park, Nojun Kwak, and Jin Young Choi, "A comprehensive overhaul of feature distillation," in Proceedings of the IEEE International Conference on Computer Vision, 2019, pp. 1921--1930.

[19]

Geoffrey Hinton, Oriol Vinyals, and Jeff Dean, "Distilling the knowledge in a neural network," arXiv preprint arXiv:1503.02531, 2015.

[20]

Subhabrata Mukherjee and Ahmed Hassan Awadallah, "Distilling transformers into simple neural networks with unlabeled transfer data," arXiv preprint arXiv:1910.01769, 2019.

[21]

Pengyi Zhang, Yunxin Zhong, and Xiaoqiong Li, "Slimyolov3: Narrower, faster and better for real-time uav applications," in Proceedings of the IEEE International Conference on Computer Vision Workshops, 2019, pp. 0--0.

[22]

Joseph Redmon and Ali Farhadi, "Yolov3: an incremental improvement (2018)," arXiv preprint arXiv:1804.02767, 1804.

[23]

Andrew G. Howard, Menglong Zhu, Bo Chen, Dmitry Kalenichenko, Weijun Wang, Tobias Weyand, Marco Andreetto, and Hartwig Adam, "Mobilenets: Efficient convolutional neural networks for mobile vision applications," CoRR, 2017.

[24]

Wei Liu, Dragomir Anguelov, Dumitru Erhan, Christian Szegedy, Scott Reed, Cheng-Yang Fu, and Alexander C Berg, "Ssd: Single shot multibox detector," in European conference on computer vision. Springer, 2016, pp. 21--37.

[25]

Kaipeng Zhang, Zhanpeng Zhang, Zhifeng Li, and Yu Qiao, "Joint face detection and alignment using multitask cascaded convolutional networks," IEEE Signal Processing Letters, vol. 23, no. 10, pp. 1499--1503, 2016.

[26]

Kaiming He, Xiangyu Zhang, Shaoqing Ren, and Jian Sun, "Delving deep into rectifiers: Surpassing human-level performance on imagenet classification," in Proceedings of the IEEE international conference on computer vision, 2015, pp. 1026--1034.

[27]

Vinod Nair and Geoffrey E Hinton, "Rectified linear units improve restricted boltzmann machines," in Proceedings of the 27th international conference on machine learning (ICML-10), 2010, pp. 807--814.

[28]

Sergey Ioffe and Christian Szegedy, "Batch normalization: Accelerating deep network training by reducing internal covariate shift," arXiv preprint arXiv:1502.03167, 2015.

[29]

Shuo Yang, Ping Luo, Chen-Change Loy, and Xiaoou Tang, "Wider face: A face detection benchmark," in Proceedings of the IEEE conference on computer vision and pattern recognition, 2016, pp. 5525--5533.

[30]

Yang He, Ping Liu, Ziwei Wang, Zhilan Hu, and Yi Yang. Filter pruning via geometric median for deep convolutional neural networks acceleration. In Proc. CVPR, pages 4340--4349, 2019.

[31]

Yihui He, Xiangyu Zhang, and Jian Sun. Channel pruning for accelerating very deep neural networks. In Proc. ICCV, pages 1389--1397, 2017.

[32]

Wei Wen, Chunpeng Wu, Yandan Wang, Yiran Chen, and Hai Li. Learning structured sparsity indeepneural networks. In Proc. NeurIPS, pages 2074--2082, 2016.

[33]

Jose M Alvarez and Mathieu Salzmann. Learning the number of neurons in deep networks. In Proce. NeurIPS, pages 2270--2278, 2016.

[34]

Dejiao Zhang, Haozhu Wang, Mario Figueiredo, and Laura Balzano. Learning to share: Simultaneous parameter tying and sparsification in deep learning. In Proc. ICLR, 2018.

[35]

Kaipeng Zhang, Zhanpeng Zhang, Zhifeng Li, and Yu Qiao. 2016. Joint Face Detection and Alignmentusing Multitask Cascaded Convolutional Networks. CoRR (2016).

[36]

Shuo Yang, Ping Luo, Chen Change Loy, and Xiaoou Tang. 2016. WiderFace: A Face Detection Benchmark. In 2016 IEEE Conference on Computer Vision and Pattern Recognition, CVPR2016, LasVegas, NV, USA, June 27-30, 2016. IEEE Computer Society, 5525--5533. https://doi.org/10.1109/CVPR.2016.596

[37]

Ganesh G. Patil and Rohitash K. Banyal, "A Dynamic Unconstrained Feature Matching Algorithm for Face Recognition," Journal of Advances in Information Technology, Vol. 11, No. 2, pp. 103--108, May 2020.

[38]

Salwa A. Al-agha, Hilal H. Saleh, and Rana F. Ghani, "Geometric-based Feature Extraction and Classification for Emotion Expressions of 3D Video Film," Vol. 8, No. 2, pp. 74--79, May, 2017.

Cited By

Gkrispanis KGkalelis NMezaris V(2024)Filter-Pruning of Lightweight Face Detectors Using a Geometric Median Criterion2024 IEEE/CVF Winter Conference on Applications of Computer Vision Workshops (WACVW)10.1109/WACVW60836.2024.00037(280-289)Online publication date: 1-Jan-2024
https://doi.org/10.1109/WACVW60836.2024.00037

Index Terms

PruneFaceDet: Pruning Lightweight Face Detection Network by Sparsity Training
1. Computing methodologies
  1. Artificial intelligence
    1. Computer vision
      1. Computer vision problems
        Object detection

Recommendations

PruneFaceDet: Pruning lightweight face detection network by sparsity training
Abstract
Face detection is the basic step of many face analysis tasks. In practice, face detectors usually run on mobile devices with limited memory and computing resources. Therefore, it is important to keep face detectors lightweight. To this end, ...
Face Recognition Based Person Specific Identification for Video Surveillance Applications
WCI '15: Proceedings of the Third International Symposium on Women in Computing and Informatics

Face detection is an important aspect for applications like biometrics, video surveillance and human computer interaction. Videos provide abundant information and also that can be leveraged by temporal variations in pose, expression changes and ...
Structured Network Pruning via Adversarial Multi-indicator Architecture Selection
Abstract
Network pruning offers an opportunity to facilitate deploying convolutional neural networks (CNNs) on resource-limited embedded devices. Pruning more redundant network structures while ensuring network accuracy is challenging. Most existing CNN ...

Comments

Information & Contributors

Information

Published In

cover image ACM Other conferences

ICCPR '20: Proceedings of the 2020 9th International Conference on Computing and Pattern Recognition

October 2020

552 pages

ISBN:9781450387835

DOI:10.1145/3436369

Copyright © 2020 ACM.

Permission to make digital or hard copies of all or part of this work for personal or classroom use is granted without fee provided that copies are not made or distributed for profit or commercial advantage and that copies bear this notice and the full citation on the first page. Copyrights for components of this work owned by others than ACM must be honored. Abstracting with credit is permitted. To copy otherwise, or republish, to post on servers or to redistribute to lists, requires prior specific permission and/or a fee. Request permissions from [email protected]

In-Cooperation

Beijing University of Technology

Publisher

Association for Computing Machinery

New York, NY, United States

Publication History

Published: 11 January 2021

Permissions

Request permissions for this article.

Request Permissions

Check for updates

Author Tags

Qualifiers

Research-article
Research
Refereed limited

Conference

ICCPR 2020

ICCPR 2020: 2020 9th International Conference on Computing and Pattern Recognition

October 30 - November 1, 2020

Xiamen, China

Contributors

Other Metrics

View Article Metrics

Bibliometrics & Citations

Bibliometrics

Article Metrics

1
Total Citations
View Citations
56
Total Downloads

Downloads (Last 12 months)3
Downloads (Last 6 weeks)0

Reflects downloads up to 08 Mar 2025

Other Metrics

View Author Metrics

Citations

Cited By

Gkrispanis KGkalelis NMezaris V(2024)Filter-Pruning of Lightweight Face Detectors Using a Geometric Median Criterion2024 IEEE/CVF Winter Conference on Applications of Computer Vision Workshops (WACVW)10.1109/WACVW60836.2024.00037(280-289)Online publication date: 1-Jan-2024
https://doi.org/10.1109/WACVW60836.2024.00037

View Options

Login options

Check if you have access through your login credentials or your institution to get full access on this article.

Full Access

Get this Publication

View options

PDF

View or Download as a PDF file.

eReader

View online with eReader.

Figures

Tables

Media

View Table of Conten