The (Un)reliability of saliency methods
arXiv: Machine Learning, Volume abs/1711.00867, 2018, Pages 267-280.
Saliency methods aim to explain the predictions of deep neural networks. These methods lack reliability when the explanation is sensitive to factors that do not contribute to the model prediction. We use a simple and common pre-processing step ---adding a mean shift to the input data--- to show that a transformation with no effect on the ...More
PPT (Upload PPT)