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

Table 4

The comparison of error rate of the classification’s results in two features extracting ways.

Features	Frequency of training	500	1000	1500
Features extracting by CNN	Error rate%	63.3	36.7	18.2
High-level features and features extracting by CNN		51.7	25.8	14.2