Discover and Mitigate Multiple Biased Subgroups in Image Classifiers

arXiv:2403.12777v1 Announce Type: new
Abstract: Machine learning models can perform well on in-distribution data but often fail on biased subgroups that are underrepresented in the training data, hindering the robustness of models for reliable applications. Such subgroups are typically unknown due to the absence of subgroup labels. Discovering biased subgroups is the key to understanding models' failure modes and further improving models' robustness. Most previous works of subgroup discovery make an implicit assumption that models only underperform on a single …

abstract applications arxiv classifiers cs.ai cs.cv data distribution image labels machine machine learning machine learning models multiple robustness subgroups training training data type