A Recurrent Temporal Model for Semantic Levels Categorization Based on Human Visual System

Figure 15

The model’s accuracy and the model’s time for vehicle images as input in 10 runs of the feedback mode and feedback-less mode for occluded images in three levels of categorization. (a) The model’s accuracy of occluded images of car and motorcycle. (b) The model’s time of occluded images of car and motorcycle. (c) The model’s accuracy of occluded images of the airplane and the helicopter. (d) The model’s time of occluded images of the airplane and the helicopter.

(a)

(b)

(c)

(d)