A Simple Technique to Enable Saliency Methods to Pass the Sanity Checks

ICLR 2020 Anonymous

{\em Saliency methods} attempt to explain a deep net's decision by assigning a {\em score} to each feature/pixel in the input, often doing this credit-assignment via the gradient of the output with respect to input. Recently \citet{adebayosan} questioned the validity of many of these methods since they do not pass simple {\em sanity checks}, which test whether the scores shift/vanish when layers of the trained net are randomized, or when the net is retrained using random labels for inputs... (read more)

PDF Abstract


No code implementations yet. Submit your code now


Results from the Paper

  Submit results from this paper to get state-of-the-art GitHub badges and help the community compare results to other papers.