POPCORN: Progressive Pseudo-labeling with Consistency Regularization and Neighboring
Language
en
Communication dans un congrès
This item was published in
International Conference on Medical Image Computing and Computer Assisted Intervention (MICCAI'21), 2021-09-27, Strasbourg (virtual). 2021, vol. 12902, p. 373-382
Date
2021English Abstract
Semi-supervised learning (SSL) uses unlabeled data to compensate for the scarcity of annotated images and the lack of method generalization to unseen domains, two usual problems in medical segmentation tasks. In this work, ...Read more >
Semi-supervised learning (SSL) uses unlabeled data to compensate for the scarcity of annotated images and the lack of method generalization to unseen domains, two usual problems in medical segmentation tasks. In this work, we propose POPCORN, a novel method combining consistency regularization and pseudo-labeling designed for image segmentation. The proposed framework uses high-level regularization to constrain our segmentation model to use similar latent features for images with similar segmentations. POPCORN estimates a proximity graph to select data from easiest ones to more difficult ones, in order to ensure accurate pseudo-labeling and to limit confirmation bias. Applied to multiple sclerosis lesion segmentation, our method demonstrates competitive results compared to other state-of-the-art SSL strategies.Read less <
English Keywords
MS lesion segmentation
Consistency regularization
Pseudo-labeling
Semi-supervised Learning
ANR Project
Apprentissage profond pour la volumétrie cérébrale : vers le BigData en neuroscience - ANR-18-CE45-0013
Origin
Hal imported