Category-orthogonal object features guide information processing in recurrent neural networks trained for object categorization
Abstract
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 that: (a) information about auxiliary variables increases across time in all network layers, (b) this information is indeed present in the recurrent information flow, and (c) its manipulation significantly affects task performance. These observations confirm the hypothesis that category-orthogonal auxiliary variable information is conveyed through recurrent connectivity and is used to optimize category inference in cluttered environments.
Cite
@article{arxiv.2111.07898,
title = {Category-orthogonal object features guide information processing in recurrent neural networks trained for object categorization},
author = {Sushrut Thorat and Giacomo Aldegheri and Tim C. Kietzmann},
journal= {arXiv preprint arXiv:2111.07898},
year = {2022}
}
Comments
13 pages, 9 figures, peer-reviewed and accepted at the SVRHM 2021 workshop at NeurIPS (+ 2 additional sections in the Appendix presenting newer supplementary results). SVRHM 2021 Workshop@ NeurIPS. 2021