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

Figure 16

The model’s accuracy and the model’s time for occluded images of animals as the input in 10 runs of the feedback mode and feedback-less mode in three levels of categorization. (a) The model’s accuracy of occluded images of dog and cat. (b) The model’s time of occluded images of dog and cat. (c) The model’s accuracy of occluded images of dolphin and fish. (d) The model’s time of occluded images of dolphin and fish. (e) The model’s accuracy of occluded images of spider and butterfly. (f) The model’s time of occluded images of spider and butterfly.

(a)

(b)

(c)

(d)

(e)

(f)