Visual Illusions Also Deceive Convolutional Neural Networks: Analysis and Implications

12/03/2019
by   A. Gomez-Villa, et al.
8

Visual illusions allow researchers to devise and test new models of visual perception. Here we show that artificial neural networks trained for basic visual tasks in natural images are deceived by brightness and color illusions, having a response that is qualitatively very similar to the human achromatic and chromatic contrast sensitivity functions, and consistent with natural image statistics. We also show that, while these artificial networks are deceived by illusions, their response might be significantly different to that of humans. Our results suggest that low-level illusions appear in any system that has to perform basic visual tasks in natural environments, in line with error minimization explanations of visual function, and they also imply a word of caution on using artificial networks to study human vision, as previously suggested in other contexts in the vision science literature.

READ FULL TEXT

page 3

page 4

page 14

page 15

page 18

page 19

research
11/26/2018

Convolutional Neural Networks Deceived by Visual Illusions

Visual illusions teach us that what we see is not always what it is repr...
research
03/04/2019

Do Neural Networks Show Gestalt Phenomena? An Exploration of the Law of Closure

One characteristic of human visual perception is the presence of "Gestal...
research
01/28/2022

DELAUNAY: a dataset of abstract art for psychophysical and machine learning research

Image datasets are commonly used in psychophysical experiments and in ma...
research
05/03/2014

Optimal measurement of visual motion across spatial and temporal scales

Sensory systems use limited resources to mediate the perception of a gre...
research
12/16/2022

On Human Visual Contrast Sensitivity and Machine Vision Robustness: A Comparative Study

It is well established in neuroscience that color vision plays an essent...
research
05/31/2023

CVSNet: A Computer Implementation for Central Visual System of The Brain

In computer vision, different basic blocks are created around different ...
research
10/24/2019

Assisting human experts in the interpretation of their visual process: A case study on assessing copper surface adhesive potency

Deep Neural Networks are often though to lack interpretability due to th...

Please sign up or login with your details

Forgot password? Click here to reset