18 citations · 34 across the 9 of their papers we have counts for
9 papers
Expectation Maximization Pseudo Labels
Moucheng Xu, Yukun Zhou, Chen Jin +5
In this paper, we study pseudo-labelling. Pseudo-labelling employs raw inferences on unlabelled data as pseudo-labels for self-training. We elucidate the empirical successes of pse…
Bayesian Pseudo Labels: Expectation Maximization for Robust and Efficient Semi-Supervised Segmentation
Mou-Cheng Xu, Yukun Zhou, Chen Jin +5
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) al…
Learning Morphological Feature Perturbations for Calibrated Semi-Supervised Segmentation
Mou-Cheng Xu, Yu-Kun Zhou, Chen Jin +6
We propose MisMatch, a novel consistency-driven semi-supervised segmentation framework which produces predictions that are invariant to learnt feature perturbations. MisMatch consi…
VAFO-Loss: VAscular Feature Optimised Loss Function for Retinal Artery/Vein Segmentation
Yukun Zhou, Moucheng Xu, Yipeng Hu +5
Estimating clinically-relevant vascular features following vessel segmentation is a standard pipeline for retinal vessel analysis, which provides potential ocular biomarkers for bo…
Progressive Subsampling for Oversampled Data - Application to Quantitative MRI
Stefano B. Blumberg, Hongxiang Lin, Francesco Grussu +3
We present PROSUB: PROgressive SUBsampling, a deep learning based, automated methodology that subsamples an oversampled data set (e.g. multi-channeled 3D images) with minimal loss…
MisMatch: Calibrated Segmentation via Consistency on Differential Morphological Feature Perturbations with Limited Labels
Mou-Cheng Xu, Yukun Zhou, Chen Jin +4
Semi-supervised learning (SSL) is a promising machine learning paradigm to address the issue of label scarcity in medical imaging. SSL methods were originally developed in image cl…
Learning to Address Intra-segment Misclassification in Retinal Imaging
Yukun Zhou, Moucheng Xu, Yipeng Hu +4
Accurate multi-class segmentation is a long-standing challenge in medical imaging, especially in scenarios where classes share strong similarity. Segmenting retinal blood vessels i…
Dual-attention Focused Module for Weakly Supervised Object Localization
Yukun Zhou, Zailiang Chen, Hailan Shen +3
The research on recognizing the most discriminative regions provides referential information for weakly supervised object localization with only image-level annotations. However, t…
A Refined Equilibrium Generative Adversarial Network for Retinal Vessel Segmentation
Yukun Zhou, Zailiang Chen, Hailan Shen +3
Objective: Recognizing retinal vessel abnormity is vital to early diagnosis of ophthalmological diseases and cardiovascular events. However, segmentation results are highly influen…