ECINN: Efficient Counterfactuals from Invertible Neural Networks

by   Frederik Hvilshøj, et al.

Counterfactual examples identify how inputs can be altered to change the predicted class of a classifier, thus opening up the black-box nature of, e.g., deep neural networks. We propose a method, ECINN, that utilizes the generative capacities of invertible neural networks for image classification to generate counterfactual examples efficiently. In contrast to competing methods that sometimes need a thousand evaluations or more of the classifier, ECINN has a closed-form expression and generates a counterfactual in the time of only two evaluations. Arguably, the main challenge of generating counterfactual examples is to alter only input features that affect the predicted outcome, i.e., class-dependent features. Our experiments demonstrate how ECINN alters class-dependent image regions to change the perceptual and predicted class of the counterfactuals. Additionally, we extend ECINN to also produce heatmaps (ECINNh) for easy inspection of, e.g., pairwise class-dependent changes in the generated counterfactual examples. Experimentally, we find that ECINNh outperforms established methods that generate heatmap-based explanations.


page 1

page 5

page 6

page 7

page 8

page 12


Text-to-Image Models for Counterfactual Explanations: a Black-Box Approach

This paper addresses the challenge of generating Counterfactual Explanat...

Generative Counterfactual Introspection for Explainable Deep Learning

In this work, we propose an introspection technique for deep neural netw...

Counterfactual Generation with Knockoffs

Human interpretability of deep neural networks' decisions is crucial, es...

Gradient-based Counterfactual Explanations using Tractable Probabilistic Models

Counterfactual examples are an appealing class of post-hoc explanations ...

DeDUCE: Generating Counterfactual Explanations Efficiently

When an image classifier outputs a wrong class label, it can be helpful ...

Text Counterfactuals via Latent Optimization and Shapley-Guided Search

We study the problem of generating counterfactual text for a classifier ...

Consistent Counterfactuals for Deep Models

Counterfactual examples are one of the most commonly-cited methods for e...

Please sign up or login with your details

Forgot password? Click here to reset