.png){kind=icon}
返回
Expectation maximisation pseudo labels
.png){kind=icon}
OA
AI
DOI：10.1016/j.media.2024.103125.png)
.png){kind=icon}
原文求助.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
In this paper, we study pseudo -labelling. Pseudo -labelling employs raw inferences on unlabelled data as pseudolabels for self -training. We elucidate the empirical successes of pseudo -labelling by establishing a link between this technique and the Expectation Maximisation algorithm. Through this, we realise that the original pseudolabelling serves as an empirical estimation of its more comprehensive underlying formulation. Following this insight, we present a full generalisation of pseudo -labels under Bayes' theorem, termed Bayesian Pseudo Labels. Subsequently, we introduce a variational approach to generate these Bayesian Pseudo Labels, involving the learning of a threshold to automatically select high -quality pseudo labels. In the remainder of the paper, we showcase the applications of pseudo -labelling and its generalised form, Bayesian Pseudo -Labelling, in the semi -supervised segmentation of medical images. Specifically, we focus on: (1) 3D binary segmentation of lung vessels from CT volumes; (2) 2D multi -class segmentation of brain tumours from MRI volumes; (3) 3D binary segmentation of whole brain tumours from MRI volumes; and (4) 3D binary segmentation of prostate from MRI volumes. We further demonstrate that pseudo -labels can enhance the robustness of the learned representations. The code is released in the following GitHub repository: https://github.com/moucheng2017/EMSSL.
Keyword:
Pseudo labels
Bayesian deep learning
Expectation-maximisation
Semi-supervised learning
Segmentation
Generative models
Robustness
期刊
IF:
11.8
论文数:
3.9K
被引数:
2.4W
机构
引用论文
.png){kind=icon}
分享收藏Uncertainty-guided mutual consistency learning for semi-supervised medical image segmentation不确定性引导的互一致性学习半监督医学图像分割
OAAI
OAAI分享收藏 没有更多内容
没有更多内容