Shortcut Learning in Medical Image Segmentation

arXiv:2403.06748v1 Announce Type: cross
Abstract: Shortcut learning is a phenomenon where machine learning models prioritize learning simple, potentially misleading cues from data that do not generalize well beyond the training set. While existing research primarily investigates this in the realm of image classification, this study extends the exploration of shortcut learning into medical image segmentation. We demonstrate that clinical annotations such as calipers, and the combination of zero-padded convolutions and center-cropped training sets in the dataset can inadvertently serve as …

abstract arxiv beyond classification cs.cv cs.lg data eess.iv exploration image machine machine learning machine learning models medical research segmentation set shortcut simple study training type