AI RESEARCH

Deep Attention Reweighting: Post-Hoc Attention-Based Feature Aggregation in CNNs for Disentangling Core and Spurious Features under Spurious Correlations

arXiv CS.CV

ArXi:2605.20732v1 Announce Type: new Convolutional Neural Networks (CNNs) often exploit spurious correlations in datasets, learning superficially predictive yet causally irrelevant features, leading to poor generalization and fairness issues. Deep Feature Reweighting (DFR) is a post-hoc technique that reduces a trained model's reliance on spurious correlations by re