Explaning with trees: interpreting CNNs using hierarchies
This addresses the challenge of noisy or unfaithful explanations in explainable AI for users needing to understand CNN decision-making, though it appears incremental as it builds on existing segmentation approaches.
The paper tackles the problem of providing interpretable explanations for neural network reasoning in explainable AI by introducing a framework that uses hierarchical segmentation techniques for Convolutional Neural Networks, resulting in highly interpretable and faithful model explanations that surpass traditional methods.
Challenges persist in providing interpretable explanations for neural network reasoning in explainable AI (xAI). Existing methods like Integrated Gradients produce noisy maps, and LIME, while intuitive, may deviate from the model's reasoning. We introduce a framework that uses hierarchical segmentation techniques for faithful and interpretable explanations of Convolutional Neural Networks (CNNs). Our method constructs model-based hierarchical segmentations that maintain the model's reasoning fidelity and allows both human-centric and model-centric segmentation. This approach offers multiscale explanations, aiding bias identification and enhancing understanding of neural network decision-making. Experiments show that our framework, xAiTrees, delivers highly interpretable and faithful model explanations, not only surpassing traditional xAI methods but shedding new light on a novel approach to enhancing xAI interpretability.