Convolutional Neural Networks Can Be Deceived by Visual Illusions

Tools

Gomez-Villa, Alexander, Martin, Adrian, Vazquez Corral, Javier and Bertalmío, Marcelo (2020) Convolutional Neural Networks Can Be Deceived by Visual Illusions. In: 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2019-06-16 - 2019-06-20.

Preview

PDF (Accepted_Manuscript) - Accepted Version
Download (1MB) | Preview

Abstract

Visual illusions teach us that what we see is not always what is represented in the physical world. Their special nature make them a fascinating tool to test and validate any new vision model proposed. In general, current vision models are based on the concatenation of linear and non-linear operations. The similarity of this structure with the operations present in Convolutional Neural Networks (CNNs) has motivated us to study if CNNs trained for low-level visual tasks are deceived by visual illusions. In particular, we show that CNNs trained for image denoising, image deblurring, and computational color constancy are able to replicate the human response to visual illusions, and that the extent of this replication varies with respect to variation in architecture and spatial pattern size. These results suggest that in order to obtain CNNs that better replicate human behaviour, we may need to start aiming for them to better replicate visual illusions.

Item Type:	Conference or Workshop Item (Paper)
Faculty \ School:	Faculty of Science > School of Computing Sciences
Related URLs:	http://www.scopus.com/inward/record.url?... http://openaccess.thecvf.com/content_CVP...
Depositing User:	LivePure Connector
Date Deposited:	22 Feb 2020 08:26
Last Modified:	07 Mar 2024 22:33
URI:	https://ueaeprints.uea.ac.uk/id/eprint/74290
DOI:	10.1109/CVPR.2019.01259

Downloads

Downloads per month over past year

Actions (login required)

View Item