How saccadic vision might help with theinterpretability of deep networks

05/27/2021

∙

by   Iana Sereda, et al.

∙

0

∙

share

We describe how some problems (interpretability,lack of object-orientedness) of modern deep networks potentiallycould be solved by adapting a biologically plausible saccadicmechanism of perception. A sketch of such a saccadic visionmodel is proposed. Proof of concept experimental results areprovided to support the proposed approach.