Explanation by Progressive Exaggeration

11/01/2019
by   Sumedha Singla, et al.
21

As machine learning methods see greater adoption and implementation in high stakes applications such as medical image diagnosis, the need for model interpretability and explanation has become more critical. Classical approaches that assess feature importance ( saliency maps) do not explain how and why a particular region of an image is relevant to the prediction. We propose a method that explains the outcome of a classification black-box by gradually exaggerating the semantic effect of a given class. Given a query input to a classifier, our method produces a progressive set of plausible variations of that query, which gradually changes the posterior probability from its original class to its negation. These counter-factually generated samples preserve features unrelated to the classification decision, such that a user can employ our method as a "tuning knob" to traverse a data manifold while crossing the decision boundary. Our method is model agnostic and only requires the output value and gradient of the predictor with respect to its input.

READ FULL TEXT

page 6

page 8

page 10

page 11

page 12

page 17

page 18

research
01/11/2021

Explaining the Black-box Smoothly- A Counterfactual Approach

We propose a BlackBox Counterfactual Explainer that is explicitly develo...
research
01/27/2020

Black Box Explanation by Learning Image Exemplars in the Latent Feature Space

We present an approach to explain the decisions of black box models for ...
research
12/14/2020

Combining Similarity and Adversarial Learning to Generate Visual Explanation: Application to Medical Image Classification

Explaining decisions of black-box classifiers is paramount in sensitive ...
research
11/26/2021

Reinforcement Explanation Learning

Deep Learning has become overly complicated and has enjoyed stellar succ...
research
09/30/2019

Decision Explanation and Feature Importance for Invertible Networks

Deep neural networks are vulnerable to adversarial attacks and hard to i...
research
03/13/2023

Revisiting model self-interpretability in a decision-theoretic way for binary medical image classification

Interpretability is highly desired for deep neural network-based classif...
research
07/20/2018

Explaining Image Classifiers by Adaptive Dropout and Generative In-filling

Explanations of black-box classifiers often rely on saliency maps, which...

Please sign up or login with your details

Forgot password? Click here to reset