Deep learning image classifiers achieve strong predictive performance yet remain opaque in how decisions are formed. A model may predict correctly while relying on irrelevant cues, shortcut associations, peripheral structures, or device-level artifacts instead of task-relevant regions. This opacity is especially problematic on large-scale datasets, as inspecting heatmaps one sample at a time cannot scale to thousands of predictions.
We propose Relevance Based Model Decision Explainability (ReMoDEx), a framework for systematic, dataset-scale assessment of model decision behaviour in image classification. ReMoDEx defines a stepwise pipeline: model inference, target class selection, relevance map generation, heatmap standardisation, similarity-based grouping of patterns, cluster-level interpretation, and spatial relevance assessment. Local methods such as GradCAM++, Integrated Gradients, Occlusion Sensitivity, and Layerwise Relevance Propagation are each combined independently with a single global module that summarises an entire set of relevance maps into a few decision strategy clusters, replacing sample-by-sample inspection with an automatic, scalable summary.
To demonstrate ReMoDEx, we applied it to a VGG16-based classifier distinguishing COVID-19, Normal, Lung Opacity, and Viral Pneumonia. The classifier showed stable performance (86.27% test accuracy, 0.9624 test AUC). However, each explainer combined with the global module consistently produced two recurring strategies: central thoracic region decisions and border/corner sensitive decisions, indicating possible shortcut learning that conventional metrics could not reveal. Masked image validation confirmed that model confidence and predicted class changed when central or peripheral regions were occluded. Thus, ReMoDEx provides a scalable relevance-based decision assessment framework and an essential complement to accuracy-based evaluation.
Blogger's Review: ReMoDEx addresses the interpretability issues in large-scale image classification models through a systematic approach. Its innovative global module combined with various local methods effectively reveals decision strategies that traditional evaluation methods might miss, providing important insights and tools for future research.