Faithful Counterfactual Visual Explanations (FCVE)

TL;DR

This paper introduces a counterfactual explanation model for deep learning in computer vision that produces faithful, plausible, and easy-to-understand visual explanations by identifying internal concepts and making minimal necessary changes.

Contribution

It presents a novel counterfactual explanation method that balances plausibility and faithfulness, improving interpretability of deep vision models.

Findings

Produces visual explanations reflecting internal decision processes

Balances plausibility and faithfulness in explanations

Enhances interpretability of deep learning models

Abstract

Deep learning models in computer vision have made remarkable progress, but their lack of transparency and interpretability remains a challenge. The development of explainable AI can enhance the understanding and performance of these models. However, existing techniques often struggle to provide convincing explanations that non-experts easily understand, and they cannot accurately identify models' intrinsic decision-making processes. To address these challenges, we propose to develop a counterfactual explanation (CE) model that balances plausibility and faithfulness. This model generates easy-to-understand visual explanations by making minimum changes necessary in images without altering the pixel data. Instead, the proposed method identifies internal concepts and filters learned by models and leverages them to produce plausible counterfactual explanations. The provided explanations reflect the internal decision-making process of the model, thus ensuring faithfulness to the model.