To main content

Principal Feature Visualisation in Convolutional Neural Networks

Abstract

We introduce a new visualisation technique for CNNs called Principal Feature Visualisation (PFV). It uses a single forward pass of the original network to map principal features from the final convolutional layer to the original image space as RGB channels. By working on a batch of images we can extract contrasting features, not just the most dominant ones with respect to the classification. This allows us to differentiate between several features in one image in an unsupervised manner. This enables us to assess the feasibility of transfer learning and to debug a pre-trained classifier by localising misleading or missing features.
Read the publication

Category

Academic article

Language

English

Author(s)

Affiliation

  • SINTEF Digital / Smart Sensors and Microsystems
  • Norwegian University of Life Sciences

Year

2020

Published in

Lecture Notes in Computer Science (LNCS)

ISSN

0302-9743

Volume

12368

Page(s)

18 - 31

View this publication at Norwegian Research Information Repository