Reliable or Deceptive? Investigating Gated Features for Smooth Visual Explanations in CNNs

TL;DR

This paper introduces ScoreCAM++, an improved method for visual explanations in CNNs that enhances interpretability and fairness by modifying normalization and gating mechanisms, outperforming previous techniques.

Contribution

ScoreCAM++ presents a simple yet effective modification to ScoreCAM, improving visual explainability and fairness in CNNs through normalization and gating enhancements.

Findings

ScoreCAM++ outperforms ScoreCAM in interpretability accuracy.

The method improves fairness in model explanations.

Experimental results show significant performance gains.

Abstract

Deep learning models have achieved remarkable success across diverse domains. However, the intricate nature of these models often impedes a clear understanding of their decision-making processes. This is where Explainable AI (XAI) becomes indispensable, offering intuitive explanations for model decisions. In this work, we propose a simple yet highly effective approach, ScoreCAM++, which introduces modifications to enhance the promising ScoreCAM method for visual explainability. Our proposed approach involves altering the normalization function within the activation layer utilized in ScoreCAM, resulting in significantly improved results compared to previous efforts. Additionally, we apply an activation function to the upsampled activation layers to enhance interpretability. This improvement is achieved by selectively gating lower-priority values within the activation layer. Through extensive experiments and qualitative comparisons, we demonstrate that ScoreCAM++ consistently achieves notably superior performance and fairness in interpreting the decision-making process compared to both ScoreCAM and previous methods.