Abstract
Visual counterfactual explanations aim to answer "what minimal change to this image would flip the model's prediction?" and are increasingly important as vision models are deployed in safety-critical domains (e.g., medicine). Existing diffusion-based methods can produce realistic edits, but they rely on external classifiers that must work reliably on noisy images, making them fragile and hard to deploy for robust explanations.
We introduce C-VCE, a new diffusion framework that builds the classifier directly into the generative model via a concept bottleneck layer, so that counterfactuals are guided by human-interpretable features (concepts) instead of a separate noise-robust classifier that works with pixel-level edits. Our model lets users toggle on/off semantic concepts during sampling, then minimally adjusts relevant image regions while preserving the rest of the image, respecting feature correlations.
To keep edits small and controlled, we add a simple probabilistic regularizer that balances "change the prediction" against "stay close to the original", plus a gradient-based mask that confines modifications to the most relevant regions. On benchmarks such as CelebA, C-VCE matches or improves flip rates while producing counterfactuals that are visually closer to the input and less distorted than baselines that depend on separate noisy-image classifiers. These properties make C-VCE a practical tool for vision systems where users need concrete "what-if" images without having to trust an additional, noise-robust classifier. More broadly, our results suggest that exposing and controlling an internal concept layer is a promising way to make powerful generative models easier to understand and safer to use.
Blogger's Review: The C-VCE model significantly enhances the reliability and controllability of counterfactual explanations by integrating the concept layer into the generative process. This innovation not only offers greater safety for visual AI applications but also opens new avenues for model interpretability, making it worthy of broader application across various fields.