Controlling explanatory heatmap resolution and semantics via decomposition depth

Sebastian Bach, Alexander Binder, Klaus Muller, Wojciech Samek

Research output: Chapter in Book/Report/Conference proceedingConference contribution

5 Citations (Scopus)

Abstract

We present an application of the Layer-wise Relevance Propagation (LRP) algorithm to state of the art deep convolutional neural networks and Fisher Vector classifiers to compare the image perception and prediction strategies of both classifiers with the use of visualized heatmaps. Layer-wise Relevance Propagation (LRP) is a method to compute scores for individual components of an input image, denoting their contribution to the prediction of the classifier for one particular test point. We demonstrate the impact of different choices of decomposition cut-off points during the LRP-process, controlling the resolution and semantics of the heatmap on test images from the PASCAL VOC 2007 test data set.

Original languageEnglish
Title of host publication2016 IEEE International Conference on Image Processing, ICIP 2016 - Proceedings
PublisherIEEE Computer Society
Pages2271-2275
Number of pages5
Volume2016-August
ISBN (Electronic)9781467399616
DOIs
Publication statusPublished - 2016 Aug 3
Event23rd IEEE International Conference on Image Processing, ICIP 2016 - Phoenix, United States
Duration: 2016 Sep 252016 Sep 28

Other

Other23rd IEEE International Conference on Image Processing, ICIP 2016
CountryUnited States
CityPhoenix
Period16/9/2516/9/28

Keywords

  • Explaining Classifiers
  • Heatmapping

ASJC Scopus subject areas

  • Software
  • Computer Vision and Pattern Recognition
  • Signal Processing

Fingerprint Dive into the research topics of 'Controlling explanatory heatmap resolution and semantics via decomposition depth'. Together they form a unique fingerprint.

  • Cite this

    Bach, S., Binder, A., Muller, K., & Samek, W. (2016). Controlling explanatory heatmap resolution and semantics via decomposition depth. In 2016 IEEE International Conference on Image Processing, ICIP 2016 - Proceedings (Vol. 2016-August, pp. 2271-2275). [7532763] IEEE Computer Society. https://doi.org/10.1109/ICIP.2016.7532763