Convolutional Neural Networks Can Be Deceived by Visual Illusions

Alexander Gomez-Villa, Adrian Martin, Javier Vazquez Corral, Marcelo Bertalmío

Research output: Contribution to conferencePaperpeer-review

7 Citations (Scopus)
41 Downloads (Pure)

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.
Original languageEnglish
Pages12301-12309
Number of pages9
DOIs
Publication statusPublished - 9 Jan 2020
Event2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition: http://cvpr2019.thecvf.com/ - Long Beach, United States
Duration: 16 Jun 201920 Jun 2019
http://cvpr2019.thecvf.com/

Conference

Conference2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition
Abbreviated titleCVPR
CountryUnited States
CityLong Beach
Period16/06/1920/06/19
Internet address

Cite this