Preservational Learning Improves Self-supervised Medical Image Models by Reconstructing Diverse Contexts

Preserving maximal information is one of principles of designing self-supervised learning methodologies. To reach this goal, contrastive learning adopts an implicit way which is contrasting image pairs. However, we believe it is not fully optimal to simply use the contrastive estimation for preserva...

Full description

Saved in:
Bibliographic Details
Main Authors: Zhou, Hong-Yu, Lu, Chixiang, Yang, Sibei, Han, Xiaoguang, Yu, Yizhou
Format: Conference Proceeding
Language:English
Subjects:
and cell microscopy
biological
Codes
Computational modeling
Computer vision
Estimation
Medical
Protocols
Representation learning
Task analysis
Online Access:Request full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Preserving maximal information is one of principles of designing self-supervised learning methodologies. To reach this goal, contrastive learning adopts an implicit way which is contrasting image pairs. However, we believe it is not fully optimal to simply use the contrastive estimation for preservation. Moreover, it is necessary and complemental to introduce an explicit solution to preserve more information. From this perspective, we introduce Preservational Learning to reconstruct diverse image contexts in order to preserve more information in learned representations. Together with the contrastive loss, we present Preservational Contrastive Representation Learning (PCRL) for learning self-supervised medical representations. PCRL provides very competitive results under the pretraining-finetuning protocol, outperforming both self-supervised and supervised counterparts in 5 classification/segmentation tasks substantially. Codes are available at https://github.com/Luchixiang/PCRL.
ISSN:2380-7504
DOI:10.1109/ICCV48922.2021.00348