'Artiphysiology' reveals V4-like shape tuning in a deep network trained for image classification

Abstract
Data availability
Article and author information
Metrics

Abstract

Deep networks provide a potentially rich interconnection between neuroscientific and artificial approaches to understanding visual intelligence, but the relationship between artificial and neural representations of complex visual form has not been elucidated at the level of single-unit selectivity. Taking the approach of an electrophysiologist to characterizing single CNN units, we found many units exhibit translation-invariant boundary curvature selectivity approaching that of exemplar neurons in the primate mid-level visual area V4. For some V4-like units, particularly in middle layers, the natural images that drove them best were qualitatively consistent with selectivity for object boundaries. Our results identify a novel image-computable model for V4 boundary curvature selectivity and suggest that such a representation may begin to emerge within an artificial network trained for image categorization, even though boundary information was not provided during training. This raises the possibility that single-unit selectivity in CNNs will become a guide for understanding sensory cortex.

Data availability

No new datasets were generated in the course of this research. The model this research is based on is openly available from the Berkeley Artificial Intelligence Lab.

The following previously published data sets were used

(2014) BVLC reference caffenet
BAIR BVLC CaffeNet Model.

http://dl.caffe.berkeleyvision.org/bvlc_reference_caffenet.caffemodel

Article and author information

Author details

Dean A Pospisil

Department of Biological Structure, University of Washington, Seattle, United States

For correspondence
deanp3@uw.edu

Competing interests
The authors declare that no competing interests exist.

"This ORCID iD identifies the author of this article:" 0000-0002-5793-2517
Anitha Pasupathy

Department of Biological Structure, University of Washington, Seattle, United States

Competing interests
The authors declare that no competing interests exist.

"This ORCID iD identifies the author of this article:" 0000-0003-3808-8063
Wyeth Bair

Department of Biological Structure, University of Washington, Seattle, United States

Competing interests
The authors declare that no competing interests exist.

Funding

National Science Foundation (Graduate Research Fellowship)

Dean A Pospisil

National Science Foundation (CRCNS Grant IIS-1309725)

Anitha Pasupathy
Wyeth Bair

Google (Google Faculty Research Award)

Wyeth Bair

National Institutes of Health (Grant R01 EY-018839)

Anitha Pasupathy

National Institutes of Health Office of Research Infrastructure Programs (Grant RR-00166 to the Washington National Primate Research Center)

Anitha Pasupathy

The funders had no role in study design, data collection and interpretation, or the decision to submit the work for publication.

Ethics

Animal experimentation: All animal procedures for this study, including implants, surgeries and behavioral training, conformed to NIH and USDA guidelines and were performed under an institutionally approved protocol at the Johns Hopkins University (Pasupathy and Connor, 2001) protocol #PR98A63 and the University of Washington (El-Shamayleh and Pasupathy, 2016) UW protocol #4133-01.

Copyright

This article is distributed under the terms of the Creative Commons Attribution License permitting unrestricted use and redistribution provided that the original author and source are credited.