Machine learning systems are known to be sensitive to spurious correlations between non-
essential features of the inputs (eg, background, texture, and secondary objects) and the …

Deep learning models are effective, yet brittle. Even carefully trained, their behavior tends to
be hard to predict when confronted with out-of-distribution samples. In this work, our goal is …

Deep neural networks trained via empirical risk minimization often exhibit significant
performance disparities across groups, particularly when group and task labels are …

Performance disparities across sub-populations are known to exist in deep learning-based
vision recognition models, but previous work has largely addressed such fairness concerns …

Background Understanding the mechanisms of algorithmic bias is highly challenging due to
the complexity and uncertainty of how various unknown sources of bias impact deep …

Computer vision systems have witnessed rapid progress over the past two decades due to
multiple advances in the field. As these systems are increasingly being deployed in high …

Error slice discovery associates structured patterns with model errors. Existing methods
discover error slices by clustering the error-prone samples with similar patterns or assigning …

The widespread success of deep learning models today is owed to the curation of extensive
datasets significant in size and complexity. However, such models frequently pick up …

Deep neural networks trained via empirical risk minimisation often exhibit significant
performance disparities across groups, particularly when group and task labels are …

Shortcuts, also described as Clever Hans behavior, spurious correlations, or confounders,
present a significant challenge in machine learning and AI, critically affecting model …