Baseline Computation for Attribution Methods Based on Interpolated Inputs
arXiv:2204.06120
Abstract
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, we test it with our novel Riemann-Stieltjes Integrated Gradient-weighted Class Activation Mapping (RSI-Grad-CAM) attribution method.
6 pages, 3 figures