Train, Learn, Expand, Repeat.

Published in ICLR 2020 workshop on AI for Affordable Healthcare., 2020

Parida, A., Sankar, A., Eisawy, R., Finck, T., Wiestler, B., Pfister, F., & Moosbauer, J. (2020). Train, Learn, Expand, Repeat. arXiv preprint arXiv:2003.08469. https://arxiv.org/pdf/2003.08469

In this work, We propose a recursive training strategy to perform the task of semantic segmentation given only very few training samples with pixel-level annotations. We expand on this small training set having cheaper image-level annotations using a recursive training strategy. We apply this technique on the segmentation of intracranial hemorrhage (ICH) in CT (computed tomography) scans of the brain, where typically few annotated data is available.

Read the complete paper on arXiv.

Published as a workshop paper at AI for Affordable Healthcare, ICLR 2020.