A Progressive Learning Framework for Unconstrained Face Recognition

被引：0
|
作者：
Chai, Zhenhua [1 ]
Li, Shengxi [1 ]
Meng, Huanhuan [1 ]
Lai, Shenqi [1 ]
Wei, Xiaoming [1 ]
Zhang, Jianwei [1 ]
机构：
[1] Vison & Image Ctr VIC Meituan, Beijing, Peoples R China
来源：
2019 IEEE/CVF INTERNATIONAL CONFERENCE ON COMPUTER VISION WORKSHOPS (ICCVW) | 2019年
关键词：
MARGIN SOFTMAX;
D O I：
10.1109/ICCVW.2019.00331
中图分类号：
TP18 [人工智能理论];
学科分类号：
081104 ; 0812 ; 0835 ; 1405 ;
摘要：
The carefully designed backbone network, the increase of training data and the improved training skills have boosted the performance of modern face recognition systems. However, in some deployment cases which aim at model compactness and energy efficiency, some of the existing systems may fail due to the high complexity. Lightweight Face Recognition Challenge is proposed in order to make some progress in this direction and establishes a new comprehensive benchmark. In this challenge, we have designed a light weight backbone architecture and all the parameters are trained in a progressive way. Finally we achieve the 5th in track 1 and the 4th in track 3.
引用
收藏
页码：2703 / 2710
页数：8
相关论文
共 50 条
  • [41] Deep compact discriminative representation for unconstrained face recognition
    Zhang, Monica M. Y.
    Shang, Kun
    Wu, Huaming
    SIGNAL PROCESSING-IMAGE COMMUNICATION, 2019, 75 : 118 - 127
  • [42] Face recognition from unconstrained images: Progress with prototypes
    Jenkins, Rob
    Burton, A. Mike
    White, David
    PROCEEDINGS OF THE SEVENTH INTERNATIONAL CONFERENCE ON AUTOMATIC FACE AND GESTURE RECOGNITION - PROCEEDINGS OF THE SEVENTH INTERNATIONAL CONFERENCE, 2006, : 25 - +
  • [43] Discriminative Sparsity Graph Embedding for Unconstrained Face Recognition
    Tong, Ying
    Zhang, Jiachao
    Chen, Rui
    ELECTRONICS, 2019, 8 (05)
  • [44] Variability Compensation Using NAP for Unconstrained Face Recognition
    Tome, Pedro
    Vera-Rodriguez, Ruben
    Fierrez, Julian
    Ortega-Garcia, Javier
    DISTRIBUTED COMPUTING AND ARTIFICIAL INTELLIGENCE, 2012, 151 : 129 - 139
  • [45] Still-to-video face recognition in unconstrained environments
    Wang, Haoyu
    Liu, Changsong
    Ding, Xiaoqing
    IMAGE PROCESSING: MACHINE VISION APPLICATIONS VIII, 2015, 9405
  • [46] Unified framework of subspace and distance metric learning for face recognition
    Liu, Qingshan
    Metaxas, Dimitris N.
    ANALYSIS AND MODELING OF FACES AND GESTURES, PROCEEDINGS, 2007, 4778 : 250 - 260
  • [47] Implementation of Face Recognition Based on Deep Learning Framework Caffe
    Zhu, Zijiang
    Deng, Xiaoguang
    Hu, Yi
    Liu, Dong
    Li, Junshan
    PROCEEDINGS OF THE 2018 INTERNATIONAL CONFERENCE ON MECHANICAL, ELECTRONIC, CONTROL AND AUTOMATION ENGINEERING (MECAE 2018), 2018, 149 : 829 - 834
  • [48] Towards unconstrained face recognition from image sequences
    Howell, AJ
    Buxton, H
    PROCEEDINGS OF THE SECOND INTERNATIONAL CONFERENCE ON AUTOMATIC FACE AND GESTURE RECOGNITION, 1996, : 224 - 229
  • [49] Quality-based Representation for Unconstrained Face Recognition
    Mendez-Llanes, Nelson
    Castillo-Rosado, Katy
    Mendez-Vazquez, Heydi
    Tistarelli, Massimo
    2020 25TH INTERNATIONAL CONFERENCE ON PATTERN RECOGNITION (ICPR), 2021, : 6494 - 6500
  • [50] Automatic face region tracking for highly accurate face recognition in unconstrained environments
    Kim, YO
    Paik, J
    Heo, J
    Koschan, A
    Abidi, B
    Abidi, M
    IEEE CONFERENCE ON ADVANCED VIDEO AND SIGNAL BASED SURVEILLANCE, PROCEEDINGS, 2003, : 29 - 36
12345