SCE-LITE-HQ: Smooth visual counterfactual explanations with generative foundation models
This addresses the need for interpretable AI in visual domains by providing a scalable solution for counterfactual explanations, though it is incremental as it builds on existing methods with improvements in efficiency and quality.
The paper tackled the problem of generating counterfactual explanations for neural networks in high-dimensional visual domains by proposing SCE-LITE-HQ, a scalable framework that leverages pretrained generative foundation models without task-specific retraining, resulting in valid, realistic, and diverse counterfactuals competitive with or outperforming existing baselines while avoiding computational overhead.
Modern neural networks achieve strong performance but remain difficult to interpret in high-dimensional visual domains. Counterfactual explanations (CFEs) provide a principled approach to interpreting black-box predictions by identifying minimal input changes that alter model outputs. However, existing CFE methods often rely on dataset-specific generative models and incur substantial computational cost, limiting their scalability to high-resolution data. We propose SCE-LITE-HQ, a scalable framework for counterfactual generation that leverages pretrained generative foundation models without task-specific retraining. The method operates in the latent space of the generator, incorporates smoothed gradients to improve optimization stability, and applies mask-based diversification to promote realistic and structurally diverse counterfactuals. We evaluate SCE-LITE-HQ on natural and medical datasets using a desiderata-driven evaluation protocol. Results show that SCE-LITE-HQ produces valid, realistic, and diverse counterfactuals competitive with or outperforming existing baselines, while avoiding the overhead of training dedicated generative models.