Assessing Fidelity in XAI post-hoc techniques: A Comparative Study with Ground Truth Explanations Datasets
This work addresses the challenge of assessing XAI method fidelity for researchers and practitioners, enabling the elimination of low-fidelity techniques to promote more trustworthy AI, but it is incremental as it builds on existing datasets and methods.
The study tackled the problem of evaluating fidelity in XAI post-hoc techniques by introducing three novel image datasets with ground truth explanations, finding that backpropagation-based methods yield higher accuracy and reliability compared to sensitivity analysis or CAM methods, though they produce noisier saliency maps.
The evaluation of the fidelity of eXplainable Artificial Intelligence (XAI) methods to their underlying models is a challenging task, primarily due to the absence of a ground truth for explanations. However, assessing fidelity is a necessary step for ensuring a correct XAI methodology. In this study, we conduct a fair and objective comparison of the current state-of-the-art XAI methods by introducing three novel image datasets with reliable ground truth for explanations. The primary objective of this comparison is to identify methods with low fidelity and eliminate them from further research, thereby promoting the development of more trustworthy and effective XAI techniques. Our results demonstrate that XAI methods based on the backpropagation of output information to input yield higher accuracy and reliability compared to methods relying on sensitivity analysis or Class Activation Maps (CAM). However, the backpropagation method tends to generate more noisy saliency maps. These findings have significant implications for the advancement of XAI methods, enabling the elimination of erroneous explanations and fostering the development of more robust and reliable XAI.