On Pixel-Wise Explanations for Non-Linear Classifier Decisions by Layer-Wise Relevance Propagation.
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 succ...
Main Authors: | Sebastian Bach, Alexander Binder, Grégoire Montavon, Frederick Klauschen, Klaus-Robert Müller, Wojciech Samek |
---|---|
Format: | Article |
Language: | English |
Published: |
Public Library of Science (PLoS)
2015-01-01
|
Series: | PLoS ONE |
Online Access: | http://europepmc.org/articles/PMC4498753?pdf=render |
Similar Items
-
Generating Hard Examples for Pixel-Wise Classification
by: Hyungtae Lee, et al.
Published: (2021-01-01) -
Pixel-Wise Classification in Hippocampus Histological Images
by: Alfonso Vizcaíno, et al.
Published: (2021-01-01) -
Pixel-Wise Motion Segmentation for SLAM in Dynamic Environments
by: Thorsten Hempel, et al.
Published: (2020-01-01) -
Explaining CNN and RNN Using Selective Layer-Wise Relevance Propagation
by: Yeon-Jee Jung, et al.
Published: (2021-01-01) -
COMBINED PATCH-WISE MINIMAL-MAXIMAL PIXELS REGULARIZATION FOR DEBLURRING
by: J. Han, et al.
Published: (2020-08-01)