Identification Rate vs. Distractors Size


Algorithm Date Submitted Set 1 Set 2 Set 3 Data Set Size
TencentAILab FaceCNN v1 08/30/2017 77.068% 77.068% 77.068% Large
Yang Sun (Reported by Author) 09/15/2016 75.786% Large
GRCCV - GRCCV 09/15/2016 75.772% 75.772% 75.772% Large
NEC - (Kihyuk Sohn/Xiang Yu/Manmohan Chandraker) 09/15/2016 62.122% 62.122% 62.122% Large
Team 2009 - (GT-CMU-SYSU) 09/15/2016 58.933% 58.933% 58.933% Large
3DiVi - (Andrey Bich/Andrey Tsybulevsky) 09/15/2016 57.045% 57.045% 57.045% Large
VeraID - (Daniel Saez Trigueros) 09/15/2016 44.191% 44.191% 44.191% Large
TSEC - (Haiyong Sun) 09/15/2016 28.716% 28.716% 28.716% Large
Baseline - Model C 09/15/2016 5.357% 5.357% 5.357% Large
Baseline - Model D 09/15/2016 3.954% 3.954% 3.954% Large
Baseline - Model A 09/15/2016 2.13% 2.13% 2.13% Large
Baseline - Model B 09/15/2016 1.846% 1.846% 1.846% Large

Rank-1 Identification Performance

Rank-10 Identification Performance





Set 1

JointBayes Verification Graph

Set 1

JointBayes Verification Graph
JointBayes Verification Graph






Set 2

JointBayes Verification Graph

Set 2

JointBayes Verification Graph






Set 3

JointBayes Verification Graph

Set 3

JointBayes Verification Graph

Identification Rank vs. Rank


Algorithm Date Submitted Set 1 Set 2 Set 3 Data Set Size
TencentAILab FaceCNN v1 08/30/2017 77.068% 77.068% 77.068% Large
Yang Sun (Reported by Author) 09/15/2016 75.786% Large
GRCCV - GRCCV 09/15/2016 75.772% 75.772% 75.772% Large
NEC - (Kihyuk Sohn/Xiang Yu/Manmohan Chandraker) 09/15/2016 62.122% 62.122% 62.122% Large
Team 2009 - (GT-CMU-SYSU) 09/15/2016 58.933% 58.933% 58.933% Large
3DiVi - (Andrey Bich/Andrey Tsybulevsky) 09/15/2016 57.045% 57.045% 57.045% Large
VeraID - (Daniel Saez Trigueros) 09/15/2016 44.191% 44.191% 44.191% Large
TSEC - (Haiyong Sun) 09/15/2016 28.716% 28.716% 28.716% Large
Baseline - Model C 09/15/2016 5.357% 5.357% 5.357% Large
Baseline - Model D 09/15/2016 3.954% 3.954% 3.954% Large
Baseline - Model A 09/15/2016 2.13% 2.13% 2.13% Large
Baseline - Model B 09/15/2016 1.846% 1.846% 1.846% Large

Identification Performance with 1 Million Distractors

Identification Performance with 10K Distractors





Set 1

JointBayes Verification Graph

Set 1

JointBayes Verification Graph
JointBayes Verification Graph







- -   uses large training set

Set 2

JointBayes Verification Graph

Set 2

JointBayes Verification Graph







- -   uses large training set

Set 3

JointBayes Verification Graph

Set 3

JointBayes Verification Graph

Verification


Algorithm Date Submitted Set 1 Set 2 Set 3 Data Set Size
TencentAILab FaceCNN v1 08/30/2017 90.302% 90.302% 90.302% Large
Yang Sun (Reported by Author) 09/15/2016 84.026% Large
GRCCV - GRCCV 09/15/2016 74.843% 74.843% 74.843% Large
Team 2009 - (GT-CMU-SYSU) 09/15/2016 71.124% 71.124% 71.124% Large
NEC - (Kihyuk Sohn/Xiang Yu/Manmohan Chandraker) 09/15/2016 66.845% 66.845% 66.845% Large
3DiVi - (Andrey Bich/Andrey Tsybulevsky) 09/15/2016 66.458% 66.458% 66.458% Large
VeraID - (Daniel Saez Trigueros) 09/15/2016 48.087% 48.087% 48.087% Large
TSEC - (Haiyong Sun) 09/15/2016 7.478% 7.478% 7.478% Large
Baseline - Model D 09/15/2016 3.01% 3.01% 3.01% Large
Baseline - Model C 09/15/2016 1.655% 1.655% 1.655% Large
Baseline - Model B 09/15/2016 1.351% 1.351% 1.351% Large
Baseline - Model A 09/15/2016 1.328% 1.328% 1.328% Large

Verification Performance with 1 Million Distractors

Verifification Performance with 10K Distractors





Set 1

JointBayes Verification Graph

Set 1

JointBayes Verification Graph
JointBayes Verification Graph






Set 2

JointBayes Verification Graph

Set 2

JointBayes Verification Graph






Set 3

JointBayes Verification Graph

Set 3

JointBayes Verification Graph