Search Results for author:
Found 2 papers, 1 papers with code
Mitigating Bias in Visual Transformers via Targeted Alignment
We visualize the feature space of the transformer self-attention modules and discover that a significant portion of the bias is encoded in the query matrix.
UDIS: Unsupervised Discovery of Bias in Deep Visual Recognition Models
Deep learning models have been shown to learn spurious correlations from data that sometimes lead to systematic failures for certain subpopulations.
Cannot find the paper you are looking for? You can
Submit a new open access paper.
