Decompose-and-Compose: A Compositional Approach to Mitigating Spurious Correlation

arXiv:2402.18919v1 Announce Type: cross
Abstract: While standard Empirical Risk Minimization (ERM) training is proven effective for image classification on in-distribution data, it fails to perform well on out-of-distribution samples. One of the main sources of distribution shift for image classification is the compositional nature of images. Specifically, in addition to the main object or component(s) determining the label, some other image components usually exist, which may lead to the shift of input distribution between train and test environments. More importantly, …

abstract arxiv classification correlation cs.cv cs.lg data distribution erm image images nature risk samples shift standard training type