English

Finding and Fixing Spurious Patterns with Explanations

Machine Learning 2022-08-19 v3

Abstract

Image classifiers often use spurious patterns, such as "relying on the presence of a person to detect a tennis racket, which do not generalize. In this work, we present an end-to-end pipeline for identifying and mitigating spurious patterns for such models, under the assumption that we have access to pixel-wise object-annotations. We start by identifying patterns such as "the model's prediction for tennis racket changes 63% of the time if we hide the people." Then, if a pattern is spurious, we mitigate it via a novel form of data augmentation. We demonstrate that our method identifies a diverse set of spurious patterns and that it mitigates them by producing a model that is both more accurate on a distribution where the spurious pattern is not helpful and more robust to distribution shift.

Keywords

Cite

@article{arxiv.2106.02112,
  title  = {Finding and Fixing Spurious Patterns with Explanations},
  author = {Gregory Plumb and Marco Tulio Ribeiro and Ameet Talwalkar},
  journal= {arXiv preprint arXiv:2106.02112},
  year   = {2022}
}
R2 v1 2026-06-24T02:48:50.655Z