ABOUT THIS IMAGE
The spatial pooling regions of the foveated object detector
A large number of species from primates to shrimps do not see the visual world with uniform spatial detail. An area with heightened sensitivity to spatial detail, known as the fovea in mammals is oriented through eye and head movements to scrutinize regions of interest in the visual environment. Akbas and Eckstein showed using a computer vision object detection model, that the foveated version of the model can attain similar search performance to its non-foveated version while bringing significant computational savings. The image shows the spatial pooling regions of the foveated model.
Image Credit: Emre Akbas