Investigation of Lightness Illusions in Artificial Neural Networks | Zendy

Leslie Wöhler | Zendy; Marcus Magnor | Zendy

AI Assistant Blog Pricing

Home ZAIA Blog

Open Access

Investigation of Lightness Illusions in Artificial Neural Networks

Author(s) -

Leslie Wöhler,

Marcus Magnor

Publication year - 2018

Publication title -

journal of vision

Language(s) - English

Resource type - Journals

SCImago Journal Rank - 1.126

H-Index - 113

ISSN - 1534-7362

DOI - 10.1167/18.10.174

Subject(s) - illusion , artificial intelligence , artificial neural network , computer science , convolutional neural network , perception , pattern recognition (psychology) , deep learning , task (project management) , lightness , psychology , management , neuroscience , economics

Figure 1: Overview of the investigated artificial neural networks. The images show the estimated albedo values for the task of image decomposition. Top l.t.r: Input image, ground truth information, Corney[1], [1] trained with the MIT dataset[2], our CNN trained on the same images as [1]. Bottom l.t.r: Narihira[3], Zhou[6], Nestemeyer[4], Shi[5]. Note that these results may be further refined in post-processing steps, which we do not include as we only focus on the ANNs output.

The content you want is available to Zendy users.

Already have an account? Click here to sign in.

Having issues? You can contact us here

Accelerating Research