TU Darmstadt / ULB / TUbiblio

MixFaceNets: Extremely Efficient Face Recognition Networks

Boutros, Fadi ; Damer, Naser ; Fang, Meiling ; Kirchbuchner, Florian ; Kuijper, Arjan (2021):
MixFaceNets: Extremely Efficient Face Recognition Networks.
IEEE, 2021 IEEE International Joint Conference on Biometrics (IJCB), virtual Conference, 04.-07.08.2021, ISBN 978-1-6654-3780-6,
DOI: 10.1109/IJCB52358.2021.9484374,
[Conference or Workshop Item]

Abstract

In this paper, we present a set of extremely efficient and high throughput models for accurate face verification, Mix-FaceNets which are inspired by Mixed Depthwise Convolutional Kernels. Extensive experiment evaluations on Label Face in the Wild (LFW), Age-DB, MegaFace, and IARPA Janus Benchmarks IJB-B and IJB-C datasets have shown the effectiveness of our MixFaceNets for applications requiring extremely low computational complexity. Under the same level of computation complexity (≤ 500M FLOPs), our MixFaceNets outperform MobileFaceNets on all the evaluated datasets, achieving 99.60% accuracy on LFW, 97.05% accuracy on AgeDB-30, 93.60 TAR (at FAR1e-6) on MegaFace, 90.94 TAR (at FAR1e-4) on IJB-B and 93.08 TAR (at FAR1e-4) on IJB-C. With computational complexity between 500M and 1G FLOPs, our MixFaceNets achieved results comparable to the top-ranked models, while using significantly fewer FLOPs and less computation over-head, which proves the practical value of our proposed Mix-FaceNets. All training codes, pre-trained models, and training logs have been made available https://github.com/fdbtrs/mixfacenets.

Item Type: Conference or Workshop Item
Erschienen: 2021
Creators: Boutros, Fadi ; Damer, Naser ; Fang, Meiling ; Kirchbuchner, Florian ; Kuijper, Arjan
Title: MixFaceNets: Extremely Efficient Face Recognition Networks
Language: English
Abstract:

In this paper, we present a set of extremely efficient and high throughput models for accurate face verification, Mix-FaceNets which are inspired by Mixed Depthwise Convolutional Kernels. Extensive experiment evaluations on Label Face in the Wild (LFW), Age-DB, MegaFace, and IARPA Janus Benchmarks IJB-B and IJB-C datasets have shown the effectiveness of our MixFaceNets for applications requiring extremely low computational complexity. Under the same level of computation complexity (≤ 500M FLOPs), our MixFaceNets outperform MobileFaceNets on all the evaluated datasets, achieving 99.60% accuracy on LFW, 97.05% accuracy on AgeDB-30, 93.60 TAR (at FAR1e-6) on MegaFace, 90.94 TAR (at FAR1e-4) on IJB-B and 93.08 TAR (at FAR1e-4) on IJB-C. With computational complexity between 500M and 1G FLOPs, our MixFaceNets achieved results comparable to the top-ranked models, while using significantly fewer FLOPs and less computation over-head, which proves the practical value of our proposed Mix-FaceNets. All training codes, pre-trained models, and training logs have been made available https://github.com/fdbtrs/mixfacenets.

Publisher: IEEE
ISBN: 978-1-6654-3780-6
Uncontrolled Keywords: Biometrics, Deep learning, Machine learning, Face recognition, Artificial neural networks
Divisions: 20 Department of Computer Science
20 Department of Computer Science > Interactive Graphics Systems
20 Department of Computer Science > Mathematical and Applied Visual Computing
Event Title: 2021 IEEE International Joint Conference on Biometrics (IJCB)
Event Location: virtual Conference
Event Dates: 04.-07.08.2021
Date Deposited: 03 Aug 2021 07:05
DOI: 10.1109/IJCB52358.2021.9484374
Export:
Suche nach Titel in: TUfind oder in Google
Send an inquiry Send an inquiry

Options (only for editors)
Show editorial Details Show editorial Details