Skip to main navigation Skip to search Skip to main content

HOW DO CONVNETS UNDERSTAND IMAGE INTENSITY?

Research output: Contribution to conferencePaperpeer-review

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.

Original languageEnglish (US)
StatePublished - 2023
Externally publishedYes
Event1st Tiny Papers at 11th International Conference on Learning Representations, Tiny Papers @ ICLR 2023 - Kigali, Rwanda
Duration: May 5 2023May 5 2023

Conference

Conference1st Tiny Papers at 11th International Conference on Learning Representations, Tiny Papers @ ICLR 2023
Country/TerritoryRwanda
CityKigali
Period5/5/235/5/23

All Science Journal Classification (ASJC) codes

  • Linguistics and Language
  • Language and Linguistics
  • Computer Science Applications
  • Education

Fingerprint

Dive into the research topics of 'HOW DO CONVNETS UNDERSTAND IMAGE INTENSITY?'. Together they form a unique fingerprint.

Cite this