Bayesian Pseudo Labels: Expectation Maximization for Robust and Efficient Semi-Supervised Segmentation

by   Mou-Cheng Xu, et al.

This paper concerns pseudo labelling in segmentation. Our contribution is fourfold. Firstly, we present a new formulation of pseudo-labelling as an Expectation-Maximization (EM) algorithm for clear statistical interpretation. Secondly, we propose a semi-supervised medical image segmentation method purely based on the original pseudo labelling, namely SegPL. We demonstrate SegPL is a competitive approach against state-of-the-art consistency regularisation based methods on semi-supervised segmentation on a 2D multi-class MRI brain tumour segmentation task and a 3D binary CT lung vessel segmentation task. The simplicity of SegPL allows less computational cost comparing to prior methods. Thirdly, we demonstrate that the effectiveness of SegPL may originate from its robustness against out-of-distribution noises and adversarial attacks. Lastly, under the EM framework, we introduce a probabilistic generalisation of SegPL via variational inference, which learns a dynamic threshold for pseudo labelling during the training. We show that SegPL with variational inference can perform uncertainty estimation on par with the gold-standard method Deep Ensemble.


page 7

page 13


ACPL: Anti-curriculum Pseudo-labelling forSemi-supervised Medical Image Classification

Effective semi-supervised learning (SSL) in medical im-age analysis (MIA...

Semi-supervised Contrastive Outlier removal for Pseudo Expectation Maximization (SCOPE)

Semi-supervised learning is the problem of training an accurate predicti...

Pseudo-label refinement using superpixels for semi-supervised brain tumour segmentation

Training neural networks using limited annotations is an important probl...

Deep Expectation-Maximization for Semi-Supervised Lung Cancer Screening

We present a semi-supervised algorithm for lung cancer screening in whic...

Enhancing Pseudo Label Quality for Semi-SupervisedDomain-Generalized Medical Image Segmentation

Generalizing the medical image segmentation algorithms tounseen domains ...

A Probabilistic Framework for Deep Learning

We develop a probabilistic framework for deep learning based on the Deep...

Morfessor EM+Prune: Improved Subword Segmentation with Expectation Maximization and Pruning

Data-driven segmentation of words into subword units has been used in va...