Label-Efficient Multi-Task Segmentation using Contrastive Learning

Obtaining annotations for 3D medical images is expensive and time-consuming, despite its importance for automating segmentation tasks. Although multi-task learning is considered an effective method for training segmentation models using small amounts of annotated data, a systematic understanding of...

Full description

Saved in:
Bibliographic Details
Main Authors Iwasawa, Junichiro, Hirano, Yuichiro, Sugawara, Yohei
Format Journal Article
LanguageEnglish
Published 23.09.2020
Subjects
Computer Science - Computer Vision and Pattern Recognition
Quantitative Biology - Tissues and Organs
Online AccessGet full text

Cover

More Information
Summary:Obtaining annotations for 3D medical images is expensive and time-consuming, despite its importance for automating segmentation tasks. Although multi-task learning is considered an effective method for training segmentation models using small amounts of annotated data, a systematic understanding of various subtasks is still lacking. In this study, we propose a multi-task segmentation model with a contrastive learning based subtask and compare its performance with other multi-task models, varying the number of labeled data for training. We further extend our model so that it can utilize unlabeled data through the regularization branch in a semi-supervised manner. We experimentally show that our proposed method outperforms other multi-task methods including the state-of-the-art fully supervised model when the amount of annotated data is limited.
DOI:10.48550/arxiv.2009.11160