2 papers
cs.CV2025
A Woman with a Knife or A Knife with a Woman? Measuring Directional Bias Amplification in Image Captions
Rahul Nair, Bhanu Tokas, Hannah Kerner
When we train models on biased datasets, they not only reproduce data biases, but can worsen them at test time - a phenomenon called bias amplification. Many of the current bias am…
cs.CV2024
DPA: A one-stop metric to measure bias amplification in classification datasets
Bhanu Tokas, Rahul Nair, Hannah Kerner
Most ML datasets today contain biases. When we train models on these datasets, they often not only learn these biases but can worsen them -- a phenomenon known as bias amplificatio…