Reliable or Deceptive? Investigating Gated Features for Smooth Visual Explanations in CNNs
This work addresses the need for more reliable and smooth visual explanations in deep learning models, which is crucial for users in fields requiring transparent AI, though it appears incremental as it builds upon an existing method.
The paper tackled the problem of improving visual explainability in CNNs by proposing ScoreCAM++, a modified version of ScoreCAM that alters normalization and applies activation functions to enhance interpretability, resulting in notably superior performance and fairness in interpreting model decisions.
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.