2 citations · 3 across the 6 of their papers we have counts for
6 papers
Pre or Post-Softmax Scores in Gradient-based Attribution Methods, What is Best?
Miguel Lerma, Mirtha Lucas
Gradient based attribution methods for neural networks working as classifiers use gradients of network scores. Here we discuss the practical differences between using gradients of…
A Vulnerability of Attribution Methods Using Pre-Softmax Scores
Miguel Lerma, Mirtha Lucas
We discuss a vulnerability involving a category of attribution methods used to provide explanations for the outputs of convolutional neural networks working as classifiers. It is k…
Visual Explanations from Deep Networks via Riemann-Stieltjes Integrated Gradient-based Localization
Mirtha Lucas, Miguel Lerma, Jacob Furst +1
Neural networks are becoming increasingly better at tasks that involve classifying and recognizing images. At the same time techniques intended to explain the network output have b…
Grad-CAM++ is Equivalent to Grad-CAM With Positive Gradients
Miguel Lerma, Mirtha Lucas
The Grad-CAM algorithm provides a way to identify what parts of an image contribute most to the output of a classifier deep network. The algorithm is simple and widely used for loc…
Baseline Computation for Attribution Methods Based on Interpolated Inputs
Miguel Lerma, Mirtha Lucas
We discuss a way to find a well behaved baseline for attribution methods that work by feeding a neural network with a sequence of interpolated inputs between two given inputs. Then…
Symmetry-Preserving Paths in Integrated Gradients
Miguel Lerma, Mirtha Lucas
We provide rigorous proofs that the Integrated Gradients (IG) attribution method for deep networks satisfies completeness and symmetry-preserving properties. We also study the uniq…