mlsanityData to 7 Oct 2026

MixFaceNets: Extremely Efficient Face Recognition Networks

arXiv 2107.13046 ↗First posted 27 Jul 2021cs.CVcited by 36

Not on the map. Why?

Abstract (arXiv)

In this paper, we present a set of extremely efficient and high throughput models for accurate face verification, MixFaceNets 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 overhead, which proves the practical value of our proposed MixFaceNets. All training codes, pre-trained models, and training logs have been made available https://github.com/fdbtrs/mixfacenets.

Key facts. Cited by 36 papers in the map (data through 7 Oct 2026). Builds on 19 of its 31 references that are in the map. First posted on arXiv 27 Jul 2021.

Builds on

19 of 31 references.

References · 19

  1. 2015Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shiftcited by 6,979
  2. 2018MobileNetV2: Inverted Residuals and Linear Bottleneckscited by 4,773
  3. 2017Squeeze-and-Excitation Networkscited by 4,763
  4. 2017MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applicationscited by 3,827
  5. 2015Delving Deep into Rectifiers: Surpassing Human-Level Performance on ImageNet Classificationcited by 3,590
  6. 2018ShuffleNet V2: Practical Guidelines for Efficient CNN Architecture Designcited by 1,132
  7. 2016Joint Face Detection and Alignment using Multi-task Cascaded Convolutional Networkscited by 895
  8. 2018ProxylessNAS: Direct Neural Architecture Search on Target Task and Hardwarecited by 666
  9. 2016MS-Celeb-1M: A Dataset and Benchmark for Large-Scale Face Recognitioncited by 621
  10. 2015The MegaFace Benchmark: 1 Million Faces for Recognition at Scalecited by 199
  11. 2018MobileFaceNets: Efficient CNNs for Accurate Real-Time Face Verification on Mobile Devicescited by 180
  12. 2020Partial FC: Training 10 Million Identities on a Single Machinecited by 163
7 more
  1. 2015A Light CNN for Deep Face Representation with Noisy Labelscited by 126
  2. 2019MixConv: Mixed Depthwise Convolutional Kernelscited by 108
  3. 2017Shift: A Zero FLOP, Zero Parameter Alternative to Spatial Convolutionscited by 93
  4. 2021Self-restrained Triplet Loss for Accurate Masked Face Recognitioncited by 32
  5. 2019VarGFaceNet: An Efficient Variable Group Convolutional Neural Network for Lightweight Face Recognitioncited by 30
  6. 2019AirFace: Lightweight and Efficient Model for Face Recognitioncited by 9
  7. 2019VarGNet: Variable Group Convolutional Neural Network for Efficient Embedded Computingcited by 7

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 4; 2022: 10; 2023: 11; 2024: 4; 2025: 2; 2026: 5.

36 papers.

Sort:

By area:

  1. 2022SFace: Privacy-friendly and Accurate Face Recognition using Synthetic Datacited by 63
  2. 2022Privacy-friendly Synthetic Data for the Development of Face Morphing Attack Detectorscited by 47
  3. 2023MorDIFF: Recognition Vulnerability and Attack Detectability of Face Morphing Attacks Created by Diffusion Autoencoderscited by 44
  4. 2021PocketNet: Extreme Lightweight Face Recognition Network using Neural Architecture Search and Multi-Step Knowledge Distillationcited by 36
  5. 2023EdgeFace: Efficient Face Recognition Model for Edge Devicescited by 33
  6. 2022SYN-MAD 2022: Competition on Face Morphing Attack Detection Based on Privacy-aware Synthetic Training Datacited by 30
  7. 2022QuantFace: Towards Lightweight Face Recognition by Synthetic Data Low-bit Quantizationcited by 18
  8. 2022Unsupervised Face Morphing Attack Detection via Self-paced Anomaly Detectioncited by 16
  9. 2021FocusFace: Multi-task Contrastive Learning for Masked Face Recognitioncited by 12
  10. 2023Face Morphing Attack Detection with Denoising Diffusion Probabilistic Modelscited by 12
  11. 2021Partial Attack Supervision and Regional Weighted Inference for Masked Face Presentation Attack Detectioncited by 10
  12. 2022OrthoMAD: Morphing Attack Detection Through Orthogonal Identity Disentanglementcited by 10
24 more
  1. 2023Unveiling the Two-Faced Truth: Disentangling Morphed Identities for Face Morphing Detectioncited by 9
  2. 2023SynthDistill: Face Recognition with Knowledge Distillation from Synthetic Datacited by 9
  3. 2022Face Morphing Attacks and Face Image Quality: The Effect of Morphing and the Unsupervised Attack Detection by Qualitycited by 8
  4. 2021Explainability of the Implications of Supervised and Unsupervised Face Image Quality Estimations Through Activation Map Variation Analyses in Face Recognition Modelscited by 7
  5. 2022Face Morphing Attack Detection Using Privacy-Aware Training Datacited by 7
  6. 2022OCFR 2022: Competition on Occluded Face Recognition From Synthetically Generated Structure-Aware Occlusionscited by 7
  7. 2022Towards Explaining Demographic Bias through the Eyes of Face Recognition Modelscited by 7
  8. 2023EFaR 2023: Efficient Face Recognition Competitioncited by 7
  9. 2025SelfMAD: Enhancing Generalization and Robustness in Morphing Attack Detection via Self-Supervised Learningcited by 7
  10. 2024IDNet: A Novel Dataset for Identity Document Analysis and Fraud Detectioncited by 6
  11. 2023SynFacePAD 2023: Competition on Face Presentation Attack Detection Based on Privacy-aware Synthetic Training Datacited by 5
  12. 2025xEdgeFace: Efficient Cross-Spectral Face Recognition for Edge Devicescited by 5
  13. 2023Estimating Deep Learning energy consumption based on model architecture and training environmentcited by 4
  14. 2024Model Compression Techniques in Biometrics Applications: A Surveycited by 4
  15. 2026FaceLiVTv2: An Improved Hybrid Architecture for Efficient Mobile Face Recognitioncited by 3
  16. 2023SqueezerFaceNet: Reducing a Small Face Recognition CNN Even More Via Filter Pruningcited by 2
  17. 2024Deep Network Pruning: A Comparative Study on CNNs in Face Recognitioncited by 2
  18. 2023Efficient Verification-Based Face Identificationcited by 1
  19. 2024SymFace: Additional Facial Symmetry Loss for Deep Face Recognitioncited by 1
  20. 2026Emergent Morphing Attack Detection in Open Multi-modal Large Language Modelscited by 1
  21. 2026DCMorph: Face Morphing via Dual-Stream Cross-Attention Diffusioncited by 1
  22. 2026Lightweight Cross-Spectral Face Recognition via Contrastive Alignment and Distillationcited by 1
  23. 2023Lightweight Face Recognition: An Improved MobileFaceNet Modelcited by 0
  24. 2026On the Impact of Face Segmentation-Based Background Removal on Recognition and Morphing Attack Detectioncited by 0