Скачать или смотреть [ECCV 2024 Oral][Indepth Reading]Efficient Bias Mitigation Without Privileged Information

Title: Efficient Bias Mitigation Without Privileged Information

Authors: Mateo Espinosa Zarlenga, Swami Sankaranarayanan, Jerone T. A. Andrews, Zohreh Shams, Mateja Jamnik, Alice Xiang

Abstract:
Deep neural networks trained via empirical risk minimisation often exhibit
significant performance disparities across groups, particularly when group and
task labels are spuriously correlated (e.g., "grassy background" and "cows").
Existing bias mitigation methods that aim to address this issue often either
rely on group labels for training or validation, or require an extensive
hyperparameter search. Such data and computational requirements hinder the
practical deployment of these methods, especially when datasets are too large
to be group-annotated, computational resources are limited, and models are
trained through already complex pipelines. In this paper, we propose Targeted
Augmentations for Bias Mitigation (TAB), a simple hyperparameter-free framework
that leverages the entire training history of a helper model to identify
spurious samples, and generate a group-balanced training set from which a
robust model can be trained. We show that TAB improves worst-group performance
without any group information or model selection, outperforming existing
methods while maintaining overall accuracy.