Model patching: Closing the subgroup performance gap with data augmentation

K Goel, A Gu, Y Li, C Ré - arXiv preprint arXiv:2008.06775, 2020 - arxiv.org
Classifiers in machine learning are often brittle when deployed. Particularly concerning are
models with inconsistent performance on specific subgroups of a class, eg, exhibiting …
被引用次数：74 相关文章

Model Patching: Closing the Subgroup Performance Gap with Data Augmentation

K Goel, A Gu, Y Li, C Ré - arXiv e-prints, 2020 - ui.adsabs.harvard.edu
Classifiers in machine learning are often brittle when deployed. Particularly concerning are
models with inconsistent performance on specific subgroups of a class, eg, exhibiting …

Model Patching: Closing the Subgroup Performance Gap with Data Augmentation

K Goel, A Gu, Y Li, C Re - International Conference on Learning … - openreview.net
Classifiers in machine learning are often brittle when deployed. Particularly concerning are
models with inconsistent performance on specific subgroups of a class, eg, exhibiting …