To main content

Principal Feature Visualisation in Convolutional Neural Networks

Principal Feature Visualisation in Convolutional Neural Networks

Category
Academic article
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.
Client
  • Research Council of Norway (RCN) / 259869
Language
English
Author(s)
Affiliation
  • Norwegian University of Life Sciences
  • SINTEF Digital / Smart Sensor Systems
Year
Published in
Lecture Notes in Computer Science (LNCS)
ISSN
0302-9743
Publisher
Springer
Volume
12368
Page(s)
18 - 31