Objects Classification by Learning-Based Visual Saliency Model and Convolutional Neural Network

Table 3

The error rate of the classification results by three different frequency trainings of CNN in two groups of input images.

Input images	Frequency of training	500	1000	1500
300 original images	Error rate%	73.3	50.0	36.5
Humans’ classification RoIs		63.3	36.7	18.2