Deep Attention Reweighting: Post-Hoc Attention-Based Feature Aggregation in CNNs for Disentangling Core and Spurious Features under Spurious Correlations
Researchers have developed Deep Attention Reweighting (DAR), a novel post-hoc method to improve the generalization and fairness of Convolutional Neural Networks (CNNs). DAR addresses the issue of CNNs exploiting spurious correlations in datasets by using an attention-based aggregation module to selectively suppress irrelevant features. This module replaces the standard Global Average Pooling layer and is retrained alongside the classification head, outperforming existing Deep Feature Reweighting techniques. AI
IMPACT Improves CNN generalization and fairness by reducing reliance on spurious correlations, potentially leading to more robust and equitable AI systems.