Explaining Image Classifiers Using Contrastive Counterfactuals in Generative Latent Spaces
This work addresses the need for trustworthy AI in sensitive tasks by providing a novel explanation method, though it is incremental as it builds on existing counterfactual and generative model techniques.
The paper tackles the problem of generating interpretable counterfactual explanations for black-box image classifiers to enhance transparency and address biases, introducing a method that uses pretrained generative models without retraining and demonstrates its application on face attribute classification with causal and contrastive feature attributions.
Despite their high accuracies, modern complex image classifiers cannot be trusted for sensitive tasks due to their unknown decision-making process and potential biases. Counterfactual explanations are very effective in providing transparency for these black-box algorithms. Nevertheless, generating counterfactuals that can have a consistent impact on classifier outputs and yet expose interpretable feature changes is a very challenging task. We introduce a novel method to generate causal and yet interpretable counterfactual explanations for image classifiers using pretrained generative models without any re-training or conditioning. The generative models in this technique are not bound to be trained on the same data as the target classifier. We use this framework to obtain contrastive and causal sufficiency and necessity scores as global explanations for black-box classifiers. On the task of face attribute classification, we show how different attributes influence the classifier output by providing both causal and contrastive feature attributions, and the corresponding counterfactual images.