Rank-1 Identification Accuracy with 1 Million Distractors (testing age-invariant recognition at scale)

Algorithm Set 1 Set 2 Set 3
Yang Sun (Reported by Author) 53.067%
Team 2009 - (GT-CMU-SYSU) 38.208% 38.208% 38.208%
3DiVi - (Andrey Bich/Andrey Tsybulevsky) 35.790% 35.790% 35.790%
NEC - (Kihyuk Sohn/Xiang Yu/Manmohan Chandraker) 29.294% 29.294% 29.294%
GRCCV - GRCCV 21.039% 21.039% 21.039%
VeraID - (Daniel Saez Trigueros) 16.086% 16.086% 16.086%
TSEC - (Haiyong Sun) 11.566% 11.566% 11.566%
Baseline - Model C 5.873% 5.873% 5.873%
Baseline - Model D 2.770% 2.770% 2.770%
Baseline - Model A 0.334% 0.334% 0.334%
Baseline - Model B 0.189% 0.189% 0.189%

Identification Performance with 1 Million Distractors

Identification 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

Rank-1 Identification Accuracy with 1 Million Distractors (testing age-invariant recognition at scale)

Algorithm Set 1 Set 2 Set 3
Yang Sun (Reported by Author) 53.067%
Team 2009 - (GT-CMU-SYSU) 38.208% 38.208% 38.208%
3DiVi - (Andrey Bich/Andrey Tsybulevsky) 35.790% 35.790% 35.790%
NEC - (Kihyuk Sohn/Xiang Yu/Manmohan Chandraker) 29.294% 29.294% 29.294%
GRCCV - GRCCV 21.039% 21.039% 21.039%
VeraID - (Daniel Saez Trigueros) 16.086% 16.086% 16.086%
TSEC - (Haiyong Sun) 11.566% 11.566% 11.566%
Baseline - Model C 5.873% 5.873% 5.873%
Baseline - Model D 2.770% 2.770% 2.770%
Baseline - Model A 0.334% 0.334% 0.334%
Baseline - Model B 0.189% 0.189% 0.189%

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

Verification TAR for 10-6 FAR (testing age-invariant recognition at scale)

Algorithm Set 1 Set 2 Set 3
Yang Sun (Reported by Author) 53.374%
Team 2009 - (GT-CMU-SYSU) 39.101% 39.101% 39.101%
3DiVi - (Andrey Bich/Andrey Tsybulevsky) 35.529% 35.529% 35.529%
NEC - (Kihyuk Sohn/Xiang Yu/Manmohan Chandraker) 26.398% 26.398% 26.398%
GRCCV - GRCCV 19.722% 19.722% 19.722%
VeraID - (Daniel Saez Trigueros) 14.399% 14.399% 14.399%
Baseline - Model D 3.010% 3.010% 3.010%
Baseline - Model C 2.093% 2.093% 2.093%
TSEC - (Haiyong Sun) 1.299% 1.299% 1.299%
Baseline - Model A 1.010% 1.010% 1.010%
Baseline - Model B 1.010% 1.010% 1.010%

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