Baseline Computation for Attribution Methods Based on Interpolated Inputs

Add code
Apr 13, 2022
Miguel Lerma, Mirtha Lucas
Figure 1 for Baseline Computation for Attribution Methods Based on Interpolated Inputs
Figure 2 for Baseline Computation for Attribution Methods Based on Interpolated Inputs
Figure 3 for Baseline Computation for Attribution Methods Based on Interpolated Inputs

Share this with someone who'll enjoy it:

Twitter IconFacebook IconLinkedin IconWhatsapp IconMessenger Icon

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  
View paper onarxiv icon

Share this with someone who'll enjoy it:

Twitter IconFacebook IconLinkedin IconWhatsapp IconMessenger Icon