2024
ExMap: Leveraging Explainability Heatmaps for Unsupervised Group Robustness to Spurious Correlations
CVPR 2024poster
Group robustness strategies aim to mitigate learned biases in deep learning models that arise from spurious correlations present in their training datasets. However most existing methods rely on the access to the label distribution of the groups which is time-consuming and expensive to obtain. As a…