Label Rectification Learning through Kernel Extreme Learning Machine

Table 2

Accuracy (%) on Caltech-256 dataset compared with other state-of-the-art methods.

Model	Top-1	Top-5
VGG19	70.54	87.81
ResNet18	73.22	86.96
ResNet18 with stochastic depth [32]	70.00	89.00
ResNet50	80.40	92.95
+Li et al.	82.01	93.07
+ELM	78.83	91.40
+KELM	81.96	93.27