基于快速下采样的轻量化网络设计方法及人脸识别应用

王佳皓; 徐树公; 陆恒杰

doi:10.12263/DZXB.20211031

您当前的位置：

首页 >

文章列表页 >

基于快速下采样的轻量化网络设计方法及人脸识别应用

学术论文 | 更新时间：2025-12-08

- 基于快速下采样的轻量化网络设计方法及人脸识别应用
- Lightweight Network Design and Application for Face Recognition Based on Fast Down-Sampling
- 电子学报 2023年51卷第8期页码：2226-2237
- 作者机构：
  
  上海大学通信与信息工程学院，上海 200444
- 作者简介：
  
  [ "王佳皓男，1997年生.上海大学通信与信息工程学院硕士研究生.主要研究方向为模型压缩与加速、人脸识别等.E-mail: nikkonew@shu.edu.cn" ]
  [ "徐树公（通讯作者）男，1969年生.上海大学通信与信息工程学院教授.主要研究方向为无线通信系统、模式识别与机器学习. Email: shugong@shu.edu.cn" ]
  [ "陆恒杰男，1998年生.上海大学通信与信息工程学院博士研究生.主要研究方向为深度补全、人脸属性识别和人脸识别等.E-mail: luhengjie@shu.edu.cn" ]
- 基金信息：
  
  国家自然科学基金(61871262)
- DOI：10.12263/DZXB.20211031
  中图分类号： TP391.4;
- 收稿：2021-08-01，
  
  修回：2022-01-14，
  
  纸质出版：2023-08-25
- 稿件说明：
移动端阅览
王佳皓,徐树公,陆恒杰.基于快速下采样的轻量化网络设计方法及人脸识别应用[J].电子学报,2023,51(08):2226-2237.

WANG Jia-hao,XU Shu-gong,LU Heng-jie.Lightweight Network Design and Application for Face Recognition Based on Fast Down-Sampling[J].ACTA ELECTRONICA SINICA,2023,51(08):2226-2237.
王佳皓,徐树公,陆恒杰.基于快速下采样的轻量化网络设计方法及人脸识别应用[J].电子学报,2023,51(08):2226-2237. DOI： 10.12263/DZXB.20211031.

WANG Jia-hao,XU Shu-gong,LU Heng-jie.Lightweight Network Design and Application for Face Recognition Based on Fast Down-Sampling[J].ACTA ELECTRONICA SINICA,2023,51(08):2226-2237. DOI： 10.12263/DZXB.20211031.

摘要

高精度卷积神经网络推理成本往往较高，很难在资源受限的嵌入式设备上进行实时推理.本文通过分析不同类型卷积对模型推理速度的影响因素，首次指出除了模型计算量，模型的特征图输出量也是影响推理速度的一个关键因素.而现有基于深度分离卷积的轻量化方法仅把模型的计算量作为模型轻量化指标，并未考虑特征图输出量对模型推理速度的影响.根据该发现，本文结合标准卷积提出一种基于快速下采样的模型轻量化加速方法，通过快速减少特征图尺寸来同时减少模型计算量和特征图输出量.本文方法设计的轻量化模型的特征提取能力和不同平台的推理速度均优于现有的基于深度分离卷积的轻量化方法.更进一步地，本文利用该方法针对人脸识别任务提出一个快速人脸识别模型FDFaceNet.与现有的轻量化人脸识别模型相比，FDFaceNet准确率更高，在不同平台上的推理速度更快.

Abstract

High-precision convolutional neural networks often come with high inference costs

making it difficult to perform real-time inference on resource-constrained embedded devices. We analyze the factors that influence the speed of model inference by different types of convolutions

and for the first time point out that in addition to the computational complexity of the model

the feature map throughput of the model is also a key factor affecting the inference speed. However

the existing lightweight methods based on the depth-wise separation convolution only use computational complexity as the model lightweight metric

not considering the influence of the feature map throughput on the model inference speed. Based on this discovery

we propose a model lightweight acceleration design method combined with standard convolution based on fast down-sampling module

which could reduce the computational complexity and feature map throughput of the model at the same time by rapidly reducing the size of the feature map. The performance and the inference speed on different platforms of the models designed by proposed method are better than the existing lightweight methods based on depth-wise separation convolution. Further

we utilize this method to propose a fast face recognition model FDFaceNet（Fast Down-sampling FaceNet） for face recognition tasks. Compared with the existing lightweight face recognition models

FDFaceNet has higher accuracy and faster inference speed on various platforms.

关键词

Keywords

references

LIN M B , JI R R , WANG Y , et al . HRank: Filter pruning using high-rank feature map [C ] // 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) . Piscataway : IEEE , 2020 : 1526 - 1535 .

CHEN H T , WANG Y H , XU C , et al . Data-free learning of student networks [C ] // 2019 IEEE/CVF International Conference on Computer Vision (ICCV) . Piscataway : IEEE , 2020 : 3513 - 3521 .

胡骏 , 黄启鹏 , 刘嘉昕 , 等 . 引入概率分布的深度神经网络贪婪剪枝 [J ] . 中国图象图形学报 , 2021 , 26 ( 1 ): 198 - 207 .

HU J , HUANG Q P , LIU J X , et al . Greedy pruning of deep neural networks fused with probability distribution [J ] . Journal of Image and Graphics , 2021 , 26 ( 1 ): 198 - 207 . (in Chinese)

ZHUANG B H , TAN M K , LIU J , et al . Effective training of convolutional neural networks with low-bitwidth weights and activations [J ] . IEEE Transactions on Pattern Analysis and Machine Intelligence , 2022 , 44 ( 10 ): 6140 - 6152 .

HOWARD A G , ZHU M , CHEN B , et al . MobileNets: Efficient convolutional neural networks for mobile vision applications [EB/OL ] . ( 2017-04-17 )[ 2021-08-01 ] . https://arxiv.org/abs/1704.04861 https://arxiv.org/abs/1704.04861 .

SANDLER M , HOWARD A , ZHU M L , et al . MobileNetV2: inverted residuals and linear bottlenecks [C ] // 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition . Piscataway : IEEE , 2018 : 4510 - 4520 .

MA N N , ZHANG X Y , ZHENG H T , et al . ShuffleNet V2: Practical guidelines for efficient CNN architecture design [C ] // Computer Vision - ECCV 2018: 15th European Conference . New York : ACM , 2018 : 122 - 138 .

HUMPHREY E J , BELLO J P . Rethinking automatic chord recognition with convolutional neural networks [C ] // 2012 11th International Conference on Machine Learning and Applications . Piscataway : IEEE , 2013 : 357 - 362 .

CHOLLET F . Xception: Deep learning with depthwise separable convolutions [C ] // 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) . Piscataway : IEEE , 2017 : 1800 - 1807 .

权宇 , 李志欣 , 张灿龙 , 等 . 融合深度扩张网络和轻量化网络的目标检测模型 [J ] . 电子学报 , 2020 , 48 ( 2 ): 390 - 397 .

QUAN Y , LI Z X , ZHANG C L , et al . Fusing deep dilated convolutions network and light-weight network for object detection [J ] . Acta Electronica Sinica , 2020 , 48 ( 2 ): 390 - 397 . (in Chinese)

QIU J , CHEN C , LIU S , et al . SlimConv: Reducing channel redundancy in convolutional neural networks by weights flipping [EB/OL ] .( 2020-05-16 )[ 2021-08-01 ] . https://arxiv.org/abs/2003.07469 https://arxiv.org/abs/2003.07469 .

HAN K , WANG Y H , TIAN Q , et al . GhostNet: more features from cheap operations [C ] // 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) . Piscataway : IEEE , 2020 : 1577 - 1586 .

MARTÍNEZ-DÍAZ Y , NICOLÁS-DÍAZ M , MÉNDEZ-VÁZQUEZ H , et al . Benchmarking lightweight face architectures on specific face recognition scenarios [J ] . Artificial Intelligence Review , 2021 , 54 ( 8 ): 6201 - 6244 .

张典 , 汪海涛 , 姜瑛 , 等 . 基于轻量级网络的实时人脸识别算法研究 [J ] . 计算机科学与探索 , 2020 , 14 ( 2 ): 317 - 324 .

ZHANG D , WANG H T , JIANG Y , et al . Research on real-time face recognition algorithm based on lightweight network [J ] . Journal of Frontiers of Computer Science & Technology , 2020 , 14 ( 2 ): 317 - 324 . (in Chinese)

LUO P , ZHU Z Y , LIU Z W , et al . Face model compression by distilling knowledge from neurons [C ] // Proceedings of the Thirtieth AAAI Conference on Artificial Intelligence . New York : ACM , 2016 : 3560 - 3566 .

CHEN S , LIU Y , GAO X , et al . MobileFaceNets: Efficient CNNS for accurate real-time face verification on mobile devices [M ] // Biometric Recognition . Cham : Springer International Publishing , 2018 : 428 - 438 .

MARTINDEZ-DÍAZ Y , LUEVANO L S , MENDEZ-VAZQUEZ H , et al . ShuffleFaceNet: A lightweight face architecture for efficient and highly-accurate face recognition [C ] // 2019 IEEE/CVF International Conference on Computer Vision Workshop (ICCVW) . Piscataway : IEEE , 2020 : 2721 - 2728 .

DENG J , GUO J , ZHOU Y , et al . RetinaFace: Single-stage dense face localisation in the wild [EB/OL ] . ( 2019-05-02 )[ 2021-08-01 ] . https://arxiv.org/abs/1905.00641 https://arxiv.org/abs/1905.00641 .

RADOSAVOVIC I , KOSARAJU R P , GIRSHICK R , et al . Designing network design spaces [C ] // 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) . Piscataway : IEEE , 2020 : 10425 - 10433 .

徐先峰 , 张丽 , 郎彬 , 等 . 引入感知模型的改进孪生卷积神经网络实现人脸识别算法研究 [J ] . 电子学报 , 2020 , 48 ( 4 ): 643 - 647 .

XU X F , ZHANG L , LANG B , et al . Research on inception module incorporated Siamese convolutional neural networks to realize face recognition [J ] . Acta Electronica Sinica , 2020 , 48 ( 4 ): 643 - 647 . (in Chinese)

吴长虹 , 苏剑波 , 陈叶飞 . 抗年龄干扰的人脸识别 [J ] . 电子学报 , 2018 , 46 ( 7 ): 1593 - 1600 .

WU C H , SU J B , CHEN Y F . Age invariant face recognition [J ] . Acta Electronica Sinica , 2018 , 46 ( 7 ): 1593 - 1600 . (in Chinese)

WANG H , WANG Y T , ZHOU Z , et al . CosFace: large margin cosine loss for deep face recognition [C ] // 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition . Piscataway : IEEE , 2018 : 5265 - 5274 .

DENG J K , GUO J , YANG J , et al . ArcFace: Additive angular margin loss for deep face recognition [C ] // IEEE Transactions on Pattern Analysis and Machine Intelligence . Piscataway : IEEE , 2021 : 5962 - 5979 .

SIMONYAN K , ZISSERMAN A . Very deep convolutional networks for large-scale image recognition [EB/OL ] . ( 2014-09-04 )[ 2021-08-01 ] . https://arxiv.org/abs/1409.1556 https://arxiv.org/abs/1409.1556 .

HE K M , ZHANG X Y , REN S Q , et al . Deep residual learning for image recognition [C ] // 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) . Piscataway : IEEE , 2016 : 770 - 778 .

LIU X , KAN M N , WU W L , et al . VIPLFaceNet: An open source deep face recognition SDK [J ] . Frontiers of Computer Science , 2017 , 11 ( 2 ): 208 - 218 .

WU X , HE R , SUN Z N , et al . A light CNN for deep face representation with noisy labels [J ] . IEEE Transactions on Information Forensics and Security , 2018 , 13 ( 11 ): 2884 - 2896 .

LIU W , ANGUELOV D , ERHAN D , et al . SSD: Single shot MultiBox detector [M ] // Computer Vision - ECCV 2016 . Cham : Springer International Publishing , 2016 : 21 - 37 .

浏览量

下载量

CSCD

文章被引用时，请邮件提醒。

提交

工具集

关联资源

暂无数据