Rank-1 Identification Accuracy with 1 Million Distractors

Algorithm Set 1 Set 2 Set 3
NTechLAB - facenx_large 73.300% 73.309% 73.287%
Google - FaceNet v8 70.496% 70.492% 70.551%
Beijing Faceall Co. - FaceAll_Norm_1600 64.803% 64.798% 64.826%
Beijing Faceall Co. - FaceAll_1600 63.977% 63.962% 63.993%
Barebones_FR - cnn 59.363% 59.379% 59.389%
NTechLAB - facenx_small 58.218% 58.208% 58.210%
3DiVi Company - tdvm6 33.705% 33.690% 33.667%
Joint Bayes 3.021% 3.223% 3.245%
LBP 2.326% 2.320% 2.318%

Identification Performance with 1 Million Distractors

Identification Performance with 10K Distractors





JointBayes Verification Graph

- -   uses large training set

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






JointBayes Verification Graph

- -   uses large training set

Set 3

JointBayes Verification Graph

Set 3

JointBayes Verification Graph

Rank-1 Identification Accuracy with 1 Million Distractors

Algorithm Set 1 Set 2 Set 3
NTechLAB - facenx_large 73.300% 73.309% 73.287%
Google - FaceNet v8 70.496% 70.492% 70.551%
Beijing Faceall Co. - FaceAll_Norm_1600 64.803% 64.798% 64.826%
Beijing Faceall Co. - FaceAll_1600 63.977% 63.962% 63.993%
Barebones_FR - cnn 59.363% 59.379% 59.389%
NTechLAB - facenx_small 58.218% 58.208% 58.210%
3DiVi Company - tdvm6 33.705% 33.690% 33.667%
Joint Bayes 3.021% 3.223% 3.245%
LBP 2.326% 2.320% 2.318%

Rank-1 Identification Performance

Rank-10 Identification Performance





JointBayes Verification Graph

- -   uses large training set

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






JointBayes Verification Graph

- -   uses large training set

Set 3

JointBayes Verification Graph

Set 3

JointBayes Verification Graph

Verification TAR for 10-6 FAR

Algorithm Set 1 Set 2 Set 3
Google - FaceNet v8 86.473% 86.386% 86.473%
NTechLAB - facenx_large 85.081% 85.081% 85.081%
Beijing Faceall Co. - FaceAll_Norm_1600 67.118% 67.118% 67.118%
Beijing Faceall Co. - FaceAll_1600 63.960% 64.983% 63.960%
Barebones_FR - cnn 59.036% 59.036% 59.036%
NTechLAB - facenx_small 66.366% 66.427% 66.427%
3DiVi Company - tdvm6 36.927% 37.967% 36.927%
Joint Bayes 2.173% 2.204% 2.204%
LBP 1.465% 1.465% 1.465%

Verification Performance with 1 Million Distractors

Verifification Performance with 10K Distractors





JointBayes Verification Graph

- -   uses large training set

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






JointBayes Verification Graph

- -   uses large training set

Set 3

JointBayes Verification Graph

Set 3

JointBayes Verification Graph

Analysis of Rank-1 Identification for Varying Poses

The colors represent identification accuracy going from 0(=blue)–none of the true pairs were matched to 1(=red)–all possible combinations of probe and gallery were matched per probe and gallery ages. White color indicates combinations of poses that did not exist in our test set.