Meaningfully Debugging Model Mistakes using Conceptual Counterfactual Explanations

JavaScript isn't enabled in your browser, so this file can't be opened. Enable and reload.

Test related to the presentation given on 01/11/2022 by Braian O. Dias

Email *

Student's ID/alias. *

Choose the correct statements about CCE.

PS: "model" means the model where CCE is being applied for explanations.

1 point

Needs access to training data for the concepts database

Only needs the model

Provides Low-level explanations of model mistakes

Model needs retraining with concepts

What is the linear model used in the paper to learn CAV?
*

1 point

Logistic Regression

Linear Regression

ResNet18

SVM

None of the above

What is the correct interpretation of the CCE scores for the given image? *

1 point

Increasing/adding the concept "Polka dots" in the image will fix the prediction

Decreasing/removing the concept "Polka dots" in the image will fix the prediction

Increasing/adding the concept "Stripes" in the image will fix the prediction

Decreasing/removing the concept "Stripes" in the image will fix the prediction

None of the above

Given the CCE scores below, which concept do you think explains better the prediction mistake in the image?
*

1 point

Water -0.79

Cow 0.89

Stripes 0.87

Buildings 0.82

Field 1.00

Submit

Clear form

Never submit passwords through Google Forms.

This content is neither created nor endorsed by Google. Report Abuse - Terms of Service - Privacy Policy