Search Results for author: MouCheng Xu

Found 5 papers, 3 papers with code

In-Context Ensemble Learning from Pseudo Labels Improves Video-Language Models for Low-Level Workflow Understanding

no code implementations24 Sep 2024 MouCheng Xu, Evangelos Chatzaroulas, Luc McCutcheon, Abdul Ahad, Hamzah Azeem, Janusz Marecki, Ammar Anwar

We report that in-context learning helps video-language models to generate more temporally accurate SOP, and the proposed in-context ensemble learning can consistently enhance the capabilities of the video-language models in SOP generation.

Ensemble Learning In-Context Learning

Expectation Maximization Pseudo Labels

1 code implementation2 May 2023 MouCheng Xu, Yukun Zhou, Chen Jin, Marius de Groot, Daniel C. Alexander, Neil P. Oxtoby, Yipeng Hu, Joseph Jacob

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.

Segmentation

VAFO-Loss: VAscular Feature Optimised Loss Function for Retinal Artery/Vein Segmentation

no code implementations12 Mar 2022 Yukun Zhou, MouCheng Xu, Yipeng Hu, Stefano B. Blumberg, An Zhao, Siegfried K. Wagner, Pearse A. Keane, Daniel C. Alexander

Estimating clinically-relevant vascular features following vessel segmentation is a standard pipeline for retinal vessel analysis, which provides potential ocular biomarkers for both ophthalmic disease and systemic disease.

Segmentation

Learning to Address Intra-segment Misclassification in Retinal Imaging

2 code implementations25 Apr 2021 Yukun Zhou, MouCheng Xu, Yipeng Hu, Hongxiang Lin, Joseph Jacob, Pearse A. Keane, Daniel C. Alexander

Accurate multi-class segmentation is a long-standing challenge in medical imaging, especially in scenarios where classes share strong similarity.

Retinal Vessel Segmentation Segmentation

Disentangling Human Error from Ground Truth in Segmentation of Medical Images

1 code implementation NeurIPS 2020 Le Zhang, Ryutaro Tanno, MouCheng Xu, Chen Jin, Joseph Jacob, Olga Cicarrelli, Frederik Barkhof, Daniel Alexander

In all cases, our method outperforms competing methods and relevant baselines particularly in cases where the number of annotations is small and the amount of disagreement is large.

Medical Image Segmentation Segmentation

Cannot find the paper you are looking for? You can Submit a new open access paper.