Replication Data for: Relevance propagation Results with the Caffe Network and Bag of Words classifiers as used in "On Pixel-wise Explanations for Non-Linear Classifier Decisions by Layer-wise Relevance Propaganda"

This data set contains all the example images used in the manuscript "On Pixel-wise Explanations for Non-Linear Classifier Decisions by Layer-wise Relevance Propaganda" submitted to PLOS ONE (PONE-D-14-2011), which are not part of the PASCAL VOC 2009 or polygon data sets, uploaded separately.