List your company
ResearchFormerly WizWand

Face Verification on YTF (test)

98.12Verification AccuracySeqFace
91.131292.945694.7696.5744Mar 17, 2018Apr 20, 2019May 24, 2020Jun 27, 2021Aug 1, 2022Sep 4, 2023Oct 8, 2024
Updated 8mo ago

Evaluation results

MethodLinks
SeqFaceModels=1 ResNet-64, Data=MS-Celeb-1M + Celeb-Seq2018.0398.12
SFace#Images=5.8M, Backbone=R100, Training Data=MS1MV22022.0598.06
ArcFace#Images=5.8M, Backbone=R100, Training Data=MS1MV22022.0598.02
SeqFaceModels=1 ResNet-27, Data=MS-Celeb-1M + Celeb-Seq2018.0398
SSBackbone=ResNet-1012024.1097.74
CosFaceModels=1 ResNet-64, Data=5M images2018.0397.6
CosFace#Images=5M2022.0597.6
BaselineBackbone=ResNet-1012024.1097.54
SSBackbone=ResNet-502024.1097.5
BaselineBackbone=ResNet-502024.1097.41
VGG Face#Images=2.6M2022.0597.3
Marginal Loss#Images=3.8M2022.0595.98
L2-SphereFaceModels=1 ResNet-27, Data=MS-Celeb-1M2018.0395.7
FaceNetModels=1, Data=200M images2018.0395.1
FaceNet#Images=200M2022.0595.1
SphereFaceModels=1 ResNet-64, Data=CASIA-Webface2018.0395
SphereFace#Images=0.5M2022.0595
Center FaceModels=1, Data=0.7M images2018.0394.9
Center Loss#Images=0.7M2022.0594.9
Range Loss#Images=5M2022.0593.7
DeepID2+Models=25, Data=300K images2018.0393.2
DeepID#Images=0.2M2022.0593.2
DeepFaceModels=3, Data=4M images2018.0391.4
DeepFace#Images=4.4M2022.0591.4