Search papers, labs, and topics across Lattice.
This paper introduces ReMoDEx, a systematic framework for assessing decision-making behavior in image classification models at scale, addressing the opacity of deep learning classifiers. By integrating local explanation methods with a global summarization module, ReMoDEx enables the identification of common decision strategies across large datasets, revealing potential shortcut learning that traditional metrics may overlook. The application of ReMoDEx to a VGG16 classifier for COVID-19 and related conditions demonstrated stable performance while uncovering two predominant decision strategies tied to central and peripheral image regions, highlighting the need for more nuanced evaluation methods.
ReMoDEx reveals that deep learning classifiers often rely on shortcut associations, exposing critical blind spots in conventional evaluation metrics.
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. On large scale datasets this opacity is especially problematic, since 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 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. ReMoDEx thus provides a scalable relevance based decision assessment framework and an essential complement to accuracy based evaluation.
