Detailed Information

Cited 0 time in webofscience Cited 0 time in scopus
Metadata Downloads

On Pixel-Wise Explanations for Non-Linear Classifier Decisions by Layer-Wise Relevance Propagation

Authors
Bach, SebastianBinder, AlexanderMontavon, GregoireKlauschen, FrederickMueller, Klaus-RobertSamek, Wojciech
Issue Date
10-7월-2015
Publisher
PUBLIC LIBRARY SCIENCE
Citation
PLOS ONE, v.10, no.7
Indexed
SCIE
SCOPUS
Journal Title
PLOS ONE
Volume
10
Number
7
URI
https://scholar.korea.ac.kr/handle/2021.sw.korea/93021
DOI
10.1371/journal.pone.0130140
ISSN
1932-6203
Abstract
Understanding and interpreting classification decisions of automated image classification systems is of high value in many applications, as it allows to verify the reasoning of the system and provides additional information to the human expert. Although machine learning methods are solving very successfully a plethora of tasks, they have in most cases the disadvantage of acting as a black box, not providing any information about what made them arrive at a particular decision. This work proposes a general solution to the problem of understanding classification decisions by pixel-wise decomposition of nonlinear classifiers. We introduce a methodology that allows to visualize the contributions of single pixels to predictions for kernel-based classifiers over Bag of Words features and for multilayered neural networks. These pixel contributions can be visualized as heatmaps and are provided to a human expert who can intuitively not only verify the validity of the classification decision, but also focus further analysis on regions of potential interest. We evaluate our method for classifiers trained on PASCAL VOC 2009 images, synthetic image data containing geometric shapes, the MNIST handwritten digits data set and for the pre-trained ImageNet model available as part of the Caffe open source package.
Files in This Item
There are no files associated with this item.
Appears in
Collections
Graduate School > Department of Artificial Intelligence > 1. Journal Articles

qrcode

Items in ScholarWorks are protected by copyright, with all rights reserved, unless otherwise indicated.

Altmetrics

Total Views & Downloads

BROWSE