Technical Program

Paper Detail

Paper: PS-1B.49
Session: Poster Session 1B
Location: H Fl├Ąche 1.OG
Session Time: Saturday, September 14, 16:30 - 19:30
Presentation Time:Saturday, September 14, 16:30 - 19:30
Presentation: Poster
Publication: 2019 Conference on Cognitive Computational Neuroscience, 13-16 September 2019, Berlin, Germany
Paper Title: Adding biological constraints to CNNs makes image classification more human-like and robust
Manuscript:  Click here to view manuscript
License: Creative Commons License
This work is licensed under a Creative Commons Attribution 3.0 Unported License.
DOI: https://doi.org/10.32470/CCN.2019.1212-0
Authors: Gaurav Malhotra, Benjamin Evans, Jeffrey Bowers, University of Bristol, United Kingdom
Abstract: In this study, we show that when standard convolutional neural networks (CNNs) are trained end-to-end on datasets containing low-level and spatially high-frequency features, they are susceptible to learning these potentially idiosyncratic features if they are predictive of the output class. Such features are extremely unlikely to play a major role in human object recognition, where instead a strong preference for shape is observed. Through a series of empirical studies, we show that standard CNNs cannot overcome this reliance on non-shape features merely by making training more ecologically plausible or using standard regularisation methods. However, we show that these problems can be ameliorated by forgoing end-to-end learning and processing images initially with Gabor filters, in a manner that more closely resembles biological vision.