How Do ConvNets Understand Image Intensity?

Convolutional Neural Networks (ConvNets) usually rely on edge/shape information to classify images. Visualization methods developed over the last decade confirm that ConvNets rely on edge information. We investigate situations where the ConvNet needs to rely on image intensity in addition to shape....

Full description

Saved in:
Bibliographic Details
Published in:arXiv.org 2023-07
Main Authors: Jackson Kaunismaa, Guerzhoy, Michael
Format: Article
Language:English
Subjects:
Artificial neural networks
Image classification
Visualization
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Convolutional Neural Networks (ConvNets) usually rely on edge/shape information to classify images. Visualization methods developed over the last decade confirm that ConvNets rely on edge information. We investigate situations where the ConvNet needs to rely on image intensity in addition to shape. We show that the ConvNet relies on image intensity information using visualization.
ISSN:2331-8422