A brain-inspired object-based attention network for multiobject recognition and visual reasoning.

ABSTRACT: The visual system uses sequences of selective glimpses to objects to support goal-directed behavior, but how is this attention control learned? Here we present an encoder-decoder model inspired by the interacting bottom-up and top-down visual pathways making up the recognition-attention system in the brain. At every iteration, a new glimpse is taken from the image and is processed through the "what" encoder, a hierarchy of feedforward, recurrent, and capsule layers, to obtain an object-centric (object-file) representation. This representation feeds to the "where" decoder, where the evolving recurrent representation provides top-down attentional modulation to plan subsequent glimpses and impact routing in the encoder. We demonstrate how the attention mechanism significantly improves the acc

SUBMITTER: Adeli H 

PROVIDER: S-EPMC10210512 | biostudies-literature | 2023 May

REPOSITORIES: biostudies-literature