Hilbert–Schmidt Independence Criterion Regularization Kernel Framework on Symmetric Positive Definite Manifolds

Table 2

Classification accuracy on the FERET dataset.

Methods	bd	be	bf	bg	Average
logEuc-SC	74.00	94.00	97.50	80.50	86.50
RSR-S	82.50	94.50	98.00	83.50	89.63
RSR-J	79.50	96.50	97.50	86.00	89.88
TSC	36.00	73.00	73.50	44.50	56.75
Riem-DLSC	88.25	93.50	96.50	91.75	92.50
KLRM-DL	89.50	96.00	97.00	94.00	94.13
HSIC-SL	88.00	88.50	95.00	93.00	91.13
CDL	76.50	75.00	88.50	84.50	81.13
CDL-HR	81.5	83	95	90.5	87.5
RLPP	58.40	60.00	67.00	60.50	61.48
RLPP-HR	63.50	62.00	74.50	71.50	67.88
KSLR	83.00	90.00	96.00	91.00	90.00
KSLR-HR	86.00	90.00	97.50	92.00	91.38
HRGDA	89.50	93.00	96.50	94.50	93.38