On Developing Explainable AI Evaluation Metrics for Image Classification Using Borda Count and Multiple Correlation Techniques

Deep learning models have achieved remarkable performance in various problems, including image classification. However, the complex and “black-box” nature of deep learning models leads to a lack of interpretability of model decisions and a reduced level of trust in deploying the model in the wild. Explainable AI (XAI) has emerged as a new area of research that can understand and interpret the prediction made by the model. In this direction, many XAI techniques have been developed recently, focusing on key aspects that make XAI more reliable for stakeholders: explainability, transparency, and interpretability. Despite the wide array of available explainers, ensuring the quality of their explanations and selecting the most appropriate XAI approach for specific scenarios remains a complex and ambiguous task, due to the heterogeneity of explanations for various models and the lack of ground-truth explanations. Metrics help identify the best-performing explainer for the given problem nonetheless, only minimal research is carried out in this field. Some studies leveraging human-based trials lack objective metrics and exhibit bias, while approaches proposing theoretical guidelines often lack numerical evidence for quantification. To overcome this research gap, we propose two novel collective decision-making metrics leveraging Borda Count (BC) voting rules and Multiple Correlation (MC) statistical techniques. In particular, the BC metric and MC+BC metric compare and rank explanation methods and determine which explanation is most suited for the task. Hence, it serves as a quantitative as well as qualitative assessment benchmarking tool for task-specific explainer assessment. To the best of our knowledge, the application of BC and MC are not yet reported in the XAI literature. In this article, as a pilot case study, we investigate the newly proposed ranking mechanisms for image classification tasks using four popular XAI approaches: PartitionSHAP, GradientSHAP, Gradient-weighted Class Activation Mapping (GradCAM), and Gradient-weighted Class Activation Mapping (GradCAM++). We conduct our investigation on three publicly available large-scale benchmarking image datasets: MNIST, CIFAR-10, and ImageNet. Our robust and promising experimental results highlight the task-specific effectiveness of various XAI approaches and open a new research avenue for effectively comparing explainer outcomes.