H-Sets: Hessian-Guided Discovery of Set-Level Feature Interactions in Image Classifiers

ArXi:2604.22045v1 Announce Type: cross Feature attribution methods explain the predictions of deep neural networks by assigning importance scores to individual input features. However, most existing methods focus solely on marginal effects, overlooking feature interactions, where groups of features jointly influence model output. Such interactions are especially important in image classification tasks, where semantic meaning often arises from pixel interdependencies rather than isolated features.