Nuisances via Negativa: Adjusting for Spurious Correlations via Data Augmentation. (arXiv:2210.01302v1 [cs.LG])

There exist features that are related to the label in the same way across
different settings for that task; these are semantic features or semantics.
Features with varying relationships to the label are nuisances. For example, in
detecting cows from natural images, the shape of the head is a semantic and
because images of cows often have grass backgrounds but only in certain
settings, the background is a nuisance. Relationships between a nuisance and
the label are unstable across settings …

adjusting arxiv augmentation data