Gómez Villa, AlexanderMartín, AdrianVazquez-Corral, JavierBertalmío, Marcelo2021-05-112021-05-112019Gomez Villa A, Martín A, Vazquez-Corral J, Bertalmío M. Convolutional neural networks deceived by visual illusions. In: 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR); 2019 Jun 16-20; California, USA. New Jersey: IEEE; 2019. p. 10309-17. DOI: 10.1109/CVPR.2019.012592575-7075http://hdl.handle.net/10230/47390Comunicació presentada al CVPR 2019: Conference on Computer Vision and Pattern Recognition, celebrat del 16 al 20 de juny de 2019 a California, Estats Units d'Amèrica.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.application/pdfeng© 2019 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works. http://dx.doi.org/10.1109/CVPR.2019.01259info:eu-repo/semantics/conferenceObjecthttp://dx.doi.org/10.1109/CVPR.2019.01259Low-level visionComputer vision theoryDeep learningRepresentation learninginfo:eu-repo/semantics/openAccess