Generating Counterfactual Images: Toward a C2C-VAE Approach
Ziwei Zhao, David Leake, Xiaomeng Ye, David Crandall
International Conference on Case-based Reasoning Workshop on Case-Based Reasoning for the Explanation of Intelligent Systems 2022
[download paper] Generating semi-factual and counterfactual explanations from images requires methods for extracting and adjusting appropriate image features. This short paper presents initial research on a counterfactual generation method for images based on class-to-class variational autoencoders (C2C-VAEs). Initial experiments illustrate substantial speed increase in counterfactual generation while suggesting that the method achieves reasonable counterfactual quality compared to the state of the art. The paper closes by discussing tradeoffs of the approach.