DeepAI AI Chat
Log In Sign Up

Explanation by Progressive Exaggeration

by   Sumedha Singla, et al.

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.


page 6

page 8

page 10

page 11

page 12

page 17

page 18


Explaining the Black-box Smoothly- A Counterfactual Approach

We propose a BlackBox Counterfactual Explainer that is explicitly develo...

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 ...

Reinforcement Explanation Learning

Deep Learning has become overly complicated and has enjoyed stellar succ...

Decision Explanation and Feature Importance for Invertible Networks

Deep neural networks are vulnerable to adversarial attacks and hard to i...

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

Interpretability is highly desired for deep neural network-based classif...

Explaining Image Classifiers by Adaptive Dropout and Generative In-filling

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