Contrastive Counterfactual Visual Explanations With Overdetermination

by   Adam White, et al.

A novel explainable AI method called CLEAR Image is introduced in this paper. CLEAR Image is based on the view that a satisfactory explanation should be contrastive, counterfactual and measurable. CLEAR Image explains an image's classification probability by contrasting the image with a corresponding image generated automatically via adversarial learning. This enables both salient segmentation and perturbations that faithfully determine each segment's importance. CLEAR Image was successfully applied to a medical imaging case study where it outperformed methods such as Grad-CAM and LIME by an average of 27 of "causal overdetermination" where there are multiple patches in an image, any one of which is sufficient by itself to cause the classification probability to be close to one.


page 6

page 7

page 9

page 13

page 14

page 15

page 17

page 18


Explainable Image Classification with Evidence Counterfactual

The complexity of state-of-the-art modeling techniques for image classif...

Generating Counterfactual and Contrastive Explanations using SHAP

With the advent of GDPR, the domain of explainable AI and model interpre...

Measurable Counterfactual Local Explanations for Any Classifier

We propose a novel method for explaining the predictions of any classifi...

Counterfactual Instances Explain Little

In many applications, it is important to be able to explain the decision...

Towards Relatable Explainable AI with the Perceptual Process

Machine learning models need to provide contrastive explanations, since ...

Explaining the Black-box Smoothly- A Counterfactual Approach

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

Counterfactual Explanation and Causal Inference in Service of Robustness in Robot Control

We propose an architecture for training generative models of counterfact...

Code Repositories


Counterfactual Local Explanations of AI systems

view repo

Please sign up or login with your details

Forgot password? Click here to reset