… Our first test of the role of recurrent processing in object recognition focuses on the case of
partial occlusion of images. To algorithmically and parametrically manipulate occlusion in an …

… recurrent processing, instead of global recurrent processing. … recurrent processing simply
as "PCN", while referring to the model in [63] explicitly as "PCN with global recurrent processing…

… from a model of object recognition that contains excitatory feedback, we hypothesized
that recurrent processing would promote robust recognition when objects were degraded by …

… recurrent processing is required for figure-ground segmentation during object recognition. A
… results indicated that recurrent computations are required for figure-ground segmentation of …

… recurrent dynamics might improve recognition performance in the challenging scenario of
partial occlusion. We introduce two novel occluded object recognition … We find that recurrent …

… the visual system recurrent connections are abundant. Inspired by this fact, we propose a
recurrent CNN (RCNN) for object recognition by incorporating recurrent connections into each …

… have been suggested to contribute to core object recognition. Our theory has focused on
recurrent processing under challenging object recognition conditions such as when stimuli are …

… Using multivariate MEG analysis, behavioral data, backward masking and computational
modeling, we demonstrated that recurrent processing plays a major role in object recognition …

… As outlined above, we reasoned that, if recurrent processing via vlPFC to the primate
ventral stream is critical for robust core object recognition, then inactivating parts of the vlPFC …

… is demonstrated for object recognition tasks using 100 different object categories containing
… on visual recognition tasks. The recurrent network promotes robust object recognition in this …