How do ConvNets Understand Image Intensity?

Jackson Kaunismaa, Michael Guerzhoy

Keywords: saliency maps, explainability, visualization, convolutional neural network, pixel space, guided backpropagation

TL;DR: We investigate how convolutional neural networks understand image intensity.

Abstract: 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.