Ablation Path Saliency

09/26/2022
by   Justus Sagemüller, et al.
3

Various types of saliency methods have been proposed for explaining black-box classification. In image applications, this means highlighting the part of the image that is most relevant for the current decision. We observe that several of these methods can be seen as edge cases of a single, more general procedure based on finding a particular ablation path through the classifier's domain. This gives additional geometric insight to the existing methods. We also demonstrate that this ablation path method can be used as a technique in its own right, the higher computational cost being traded against additional information given by the path.

READ FULL TEXT

page 3

page 9

page 10

page 11

page 12

page 13

page 20

research
10/08/2018

Sanity Checks for Saliency Maps

Saliency methods have emerged as a popular tool to highlight features in...
research
10/31/2022

BOREx: Bayesian-Optimization–Based Refinement of Saliency Map for Image- and Video-Classification Models

Explaining a classification result produced by an image- and video-class...
research
11/26/2021

Reinforcement Explanation Learning

Deep Learning has become overly complicated and has enjoyed stellar succ...
research
05/22/2017

Real Time Image Saliency for Black Box Classifiers

In this work we develop a fast saliency detection method that can be app...
research
05/23/2022

What You See is What You Classify: Black Box Attributions

An important step towards explaining deep image classifiers lies in the ...
research
10/21/2019

Contextual Prediction Difference Analysis

The interpretation of black-box models has been investigated in recent y...
research
10/06/2020

Visualizing Color-wise Saliency of Black-Box Image Classification Models

Image classification based on machine learning is being commonly used. H...

Please sign up or login with your details

Forgot password? Click here to reset