Category-orthogonal object features guide information processing in recurrent neural networks trained for object categorization. (arXiv:2111.07898v2 [cs.CV] UPDATED)

Web: http://arxiv.org/abs/2111.07898

Recurrent neural networks (RNNs) have been shown to perform better than
feedforward architectures in visual object categorization tasks, especially in
challenging conditions such as cluttered images. However, little is known about
the exact computational role of recurrent information flow in these conditions.
Here we test RNNs trained for object categorization on the hypothesis that
recurrence iteratively aids object categorization via the communication of
category-orthogonal auxiliary variables (the location, orientation, and scale
of the object). Using diagnostic linear readouts, we find …

arxiv category- cv features information networks neural neural networks processing