HyperAIHyperAI超神经
首页资讯论文教程数据集百科SOTALLM 模型天梯GPU 天梯顶会
全站搜索
关于
HyperAIHyperAI超神经

Face Verification On Ijb B

评估指标

TAR @ FAR=0.001
TAR @ FAR=0.01
TAR@FAR=0.0001

评测结果

各个模型在此基准测试上的表现结果

模型名称
TAR @ FAR=0.001
TAR @ FAR=0.01
TAR@FAR=0.0001
Paper TitleRepository
Arc+UNPG96.697.7%95.04Unified Negative Pair Generation toward Well-discriminative Feature Space for Face Recognition
AdaFace (MS1MV2)--95.67AdaFace: Quality Adaptive Margin for Face Recognition
SE-GV-3-g2-96.4%-GhostVLAD for set-based face recognition
VGGFace2_ft90.895.6%-VGGFace2: A dataset for recognising faces across pose and age
PartialFC(WebFace42M)--96.71Killing Two Birds with One Stone:Efficient and Robust Training of Face Recognition CNNs by Partial FC
Cos+UNPG96.597.36%94.99Unified Negative Pair Generation toward Well-discriminative Feature Space for Face Recognition
Mag+UNPG96.597.63%95.21Unified Negative Pair Generation toward Well-discriminative Feature Space for Face Recognition
AdaFace (WebFace4M)--96.03AdaFace: Quality Adaptive Margin for Face Recognition
FPN-96.5%-FacePoseNet: Making a Case for Landmark-Free Face Alignment
AdaFace (MS1MV3)--95.84AdaFace: Quality Adaptive Margin for Face Recognition
CAFace+AdaFace (WebFace4M)96.91-95.53Cluster and Aggregate: Face Recognition with Large Probe Set
QMagFace96.4897.72%94.7QMagFace: Simple and Accurate Quality-Aware Face Recognition
0 of 12 row(s) selected.