EURASIP Journal on Image and Video Processing

Table 6 Performance evaluation on the IJB-A dataset

From: Deep-learned faces: a survey

Publication	1:1 verification TAR		1:N identification TPIR
	FAR = 0.001	FAR = 0.01	FPIR = 0.01	FPIR = 0.01	Rank 1	Rank 5
VGGFace [37]	-	0.461 ± 0.077	0.670 ± 0.031	0.913 ± 0.011	-
Template [59]	0.939 ± 0.013	0.979 ± 0.004	0.774 ± 0.049	0.882 ± 0.016	0.928 ± 0.010	0.977 ± 0.004
NAN [58]	0.941 ± 0.008	0.978 ± 0.003	0.817 ± 0.041	0.917 ± 0.009	0.958 ± 0.005	0.980 ± 0.005
B-CNN [62]	-	-	0.143 ± 0.027	0.341 ± 0.032	0.588 ± 0.020	0.796 ± 0.017
DCNNmanual+metric [63]	-	0.787 ± 0.043	-	-	0.852 ± 0.018	0.937 ± 0.010

For verification, the true accept rates (TAR) vs. false-positive rates (FAR) are reported. For identification, the true-positive identification rate (TPIR) vs. false-positive identification rate (TPIR) and the rank-N accuracies are presented

Back to article page