List your company
ResearchFormerly WizWand

Face Verification on AgeDB

98.7AccuracyPFC
62.175271.657681.1490.6224Jan 23, 2018Jun 15, 2019Nov 4, 2020Mar 27, 2022Aug 17, 2023Jan 6, 2025May 29, 2026
Updated 5mo ago

Evaluation results

MethodLinks
PFCTraining Dataset=WebFace42M, Backbone=ResNet-200, Sampling Ratio=0.32022.0398.7
PFCTraining Dataset=WebFace42M, Backbone=ViT-L, Sampling Ratio=0.32022.0398.67
VPL2022.0398.6
PFCTraining Dataset=WebFace42M, Backbone=ResNet-100, Sampling Ratio=0.32022.0398.6
VPL-ArcFaceTraining Dataset=MS1MV32026.0498.6
GIFTrain Set=MS1MV2, Backbone=ResNet-1002025.0598.58
GIFTrain Set=WebFace4M, Backbone=ResNet-1002025.0598.55
WebFace42M2022.0398.53
PFCTraining Dataset=WebFace12M, Backbone=ResNet-100, Sampling Ratio=0.32022.0398.53
PFCTraining Dataset=WebFace42M, Backbone=ViT-B, Sampling Ratio=0.32022.0398.53
BroadFace2022.0398.38
ArcFaceBackbone=R100, Training Dataset=IBUG500K2018.0198.38
BroadFaceTrain Set=MS1MV2, Backbone=ResNet-1002025.0598.38
BroadFaceTraining Dataset=MS1MV22026.0498.38
CurricularFace2018.0198.37
ElasticFace-Arc+Training Dataset=MS1MV22026.0498.35
CurricularFaceBackbone=ResNet1002020.0498.32
CurricularFace2022.0398.32
CurricularFaceTrain Set=MS1MV2, Backbone=ResNet-1002025.0598.32
CurricularFaceTraining Dataset=MS1MV22026.0498.32
Sub-center2022.0398.31
ArcFace2022.0398.28
GroupFace2022.0398.28
ArcFaceTrain Set=MS1MV2, Backbone=ResNet-1002025.0598.28
GroupFaceTrain Set=MS1MV2, Backbone=ResNet-1002025.0598.28
ArcFace(m=0.50)Training Dataset=MS1MV22026.0498.28
ElasticFace-Cos+Training Dataset=MS1MV22026.0498.28
PFCTraining Dataset=WebFace42M, Backbone=ResNet-100, Sampling Ratio=0.0082022.0398.27
FunFaceTraining Dataset=MS1MV32026.0498.27
DCQ2022.0398.23
ArcFaceBackbone=R100, Training Dataset=MS1MV32018.0198.23
PartialFC(ArcFace)Training Dataset=MS1MV22026.0498.2
GIFTrain Set=WebFace4M, Backbone=ViT-base2025.0598.19
MagFaceTrain Set=MS1MV2, Backbone=ResNet-1002025.0598.17
MagFaceTraining Dataset=MS1MV22026.0498.17
AdaFaceTraining Dataset=MS1MV32026.0498.17
ArcFace2020.0498.15
WebFace12M2022.0398.15
FunFaceTraining Dataset=MS1MV22026.0498.13
CosFace2022.0398.11
CosFaceTrain Set=MS1MV2, Backbone=ResNet-1002025.0598.11
CosFace(m=0.35)Training Dataset=MS1MV22026.0498.11
AdaFace(m=0.4)Training Dataset=MS1MV22026.0498.05
PartialFC(CosFace)Training Dataset=MS1MV22026.0498.03
PFCTraining Dataset=WebFace4M, Backbone=ResNet-100, Sampling Ratio=0.32022.0398.01
MV-Arc-Softmax*Backbone=ResNet1002020.0497.95
MV-Softmax2022.0397.95
MV-Softmax2018.0197.95
MV-SoftMaxTraining Dataset=MS1MV22026.0497.95
ArcFaceTraining Dataset=WebFace4M2026.0497.95
PFCTraining Dataset=WebFace12M, Backbone=ResNet-100, Sampling Ratio=0.0132022.0397.93
ArcFaceTrain Set=WebFace4M, Backbone=ResNet-1002025.0597.93
FaceGraph2018.0197.92
VirFace2022.0397.91
DB2022.0397.9
AdaFaceTraining Dataset=WebFace4M2026.0497.9
FunFaceTraining Dataset=WebFace4M2026.0497.9
Search-Softmax2018.0197.75
PFCTraining Dataset=WebFace4M, Backbone=ResNet-100, Sampling Ratio=0.042022.0397.52
AdaFaceTrain Set=WebFace4M, Backbone=ViT-base2025.0597.48
MC-mini-AMC2022.0397.25
SST2022.0397.2
BioMetricNet2022.0396.12
AFRN2022.0395.35
CASIAVenue=(Real), Generator=/, Scale (#IDs × #Imgs)=0.49M (10.5K × 47)2026.0594.5
MorphFaceVenue=CVPR 25, Generator=DM, Scale (#IDs × #Imgs)=1.2M (24K × 50)2026.0593.27
SteerFaceVenue=(Ours), Generator=DM, Scale (#IDs × #Imgs)=1.2M (24K × 50)2026.0593.12
SteerFaceVenue=(Ours), Generator=DM, Scale (#IDs × #Imgs)=0.5M (10K × 50)2026.0592.73
UIFace*Venue=ICLR 25, Generator=DM, Scale (#IDs × #Imgs)=1.2M (10K × 50)2026.0592.51
Arc2FaceVenue=ECCV 24, Generator=DM, Scale (#IDs × #Imgs)=1.2M (20K × 50, 40K × 5)2026.0592.45
IDPerturb*Venue=CVPR 26, Generator=DM, Scale (#IDs × #Imgs)=1.2M (24K × 50)2026.0592.16
MorphFaceVenue=CVPR 25, Generator=DM, Scale (#IDs × #Imgs)=0.5M (10K × 50)2026.0591.8
CemiFaceVenue=NeurIPS 24, Generator=DM, Scale (#IDs × #Imgs)=0.5M (10K × 50)2026.0591.33
ID³Training set=CASIA, Backbone=LResNet50-IR2024.0991
ID3Venue=NeurIPS 24, Generator=DM, Scale (#IDs × #Imgs)=0.5M (10K × 50)2026.0591
UIFaceVenue=ICLR 25, Generator=DM, Scale (#IDs × #Imgs)=0.5M (10K × 50)2026.0590.95
IDPerturb*Venue=CVPR 26, Generator=DM, Scale (#IDs × #Imgs)=0.5M (10K × 50)2026.0590.28
Arc2FaceVenue=ECCV 24, Generator=DM, Scale (#IDs × #Imgs)=0.5M (10K × 50)2026.0590.18
DCFaceVenue=CVPR 23, Generator=DM, Scale (#IDs × #Imgs)=1.2M (20K × 50, 40K × 5)2026.0590.07
DCFaceTraining set=FFHQ+CASIA, Backbone=LResNet50-IR2024.0989.7
DCFaceVenue=CVPR 23, Generator=DM, Scale (#IDs × #Imgs)=0.5M (10K × 50)2026.0589.7
DRGAN2020.0488
IDiff-FaceVenue=ICCV 23, Generator=DM, Scale (#IDs × #Imgs)=0.5M (10K × 50)2026.0586.43
ID³Training set=FFHQ, Backbone=LResNet50-IR2024.0983.78
DigiFaceVenue=WACV 23, Generator=Rendering, Scale (#IDs × #Imgs)=1.2M (10K × 72, 100K × 5)2026.0581.1
ExFaceGANVenue=IJCB 23, Generator=GAN, Scale (#IDs × #Imgs)=0.5M (10K × 50)2026.0578.92
IDiff-FaceTraining set=FFHQ, Backbone=LResNet50-IR2024.0978.4
DigiFaceVenue=WACV 23, Generator=Rendering, Scale (#IDs × #Imgs)=0.5M (10K × 50)2026.0576.97
Reinforcement-guided synthetic data generation frameworkData Generation=DM, Training Set=small-scale CASIA-WebFace [54] subset2026.0476.8
Authentic CASIA-Webface [54] subsetData Generation=Authentic, Training Set=small-scale CASIA-WebFace [54] subset2026.0474.72
NegFaceDiffData Generation=DM, Training Set=small-scale CASIA-WebFace [54] subset2026.0474.68
SFace2Venue=BIOM 24, Generator=GAN, Scale (#IDs × #Imgs)=0.6M (10K × 60)2026.0574.37
SFaceVenue=IJCB 22, Generator=GAN, Scale (#IDs × #Imgs)=0.6M (10K × 60)2026.0571.68
SFaceTraining set=FFHQ, Backbone=LResNet50-IR2024.0969.87
DCFaceData Generation=GAN, Training Set=small-scale CASIA-WebFace [54] subset2026.0469.75
IDnetData Generation=GAN, Training Set=small-scale CASIA-WebFace [54] subset2026.0468.73
SFace2Data Generation=GAN, Training Set=small-scale CASIA-WebFace [54] subset2026.0468.12
SFaceData Generation=GAN, Training Set=small-scale CASIA-WebFace [54] subset2026.0466.82
IDiff-FaceData Generation=DM, Training Set=small-scale CASIA-WebFace [54] subset2026.0466.6
ID-NetTraining set=FFHQ, Backbone=LResNet50-IR2024.0963.58