paper-with-me

홈 › Papers

Uncertainty-based method for improving poorly labeled segmentation datasets

2021-02-16 · Ekaterina Redekop, Alexey Chernyavskiy

The success of modern deep learning algorithms for image segmentation heavily depends on the availability of large datasets with clean pixel-level annotations (masks), where the objects of interest are accurately delineated. Lack of time and expertise during data annotation leads to incorrect boundaries and label noise. It is known that deep convolutional neural networks (DCNNs) can memorize even completely random labels, resulting in poor accuracy. We propose a framework to train binary segmentation DCNNs using sets of unreliable pixel-level annotations. Erroneously labeled pixels are identified based on the estimated aleatoric uncertainty of the segmentation and are relabeled to the true value.

📄 PDF Abstract BibTeX arXiv:2102.08021

Code (0)

등록된 구현이 없습니다.

Tasks

Image SegmentationSegmentationSemantic Segmentation

Similar Papers 제목 키워드 기반

Semi-supervised Semantic Segmentation via Boosting Uncertainty on Unlabeled Data

2023-11-30 · Daoan Zhang, Yunhao Luo, JianGuo Zhang

We bring a new perspective to semi-supervised semantic segmentation by providing an analysis on the labeled and unlabeled distributions in training datasets. We first figure out that the distribution gap between labeled …

SegmentationSemantic SegmentationSemi-Supervised Semantic Segmentation

Anatomically-aware Uncertainty for Semi-supervised Image Segmentation

2023-10-24 · Sukesh Adiga V, Jose Dolz, Herve Lombaert

Semi-supervised learning relaxes the need of large pixel-wise labeled datasets for image segmentation by leveraging unlabeled data. A prominent way to exploit unlabeled data is to regularize model predictions. Since the …

Image SegmentationSegmentationSemantic Segmentation

Self-training with dual uncertainty for semi-supervised medical image segmentation

2023-04-10 · Zhanhong Qiu, Haitao Gan, Ming Shi, Zhongwei Huang 외

In the field of semi-supervised medical image segmentation, the shortage of labeled data is the fundamental problem. How to effectively learn image features from unlabeled images to improve segmentation accuracy is the m…

Image SegmentationMedical Image SegmentationSegmentationSemantic Segmentation+1

Exploring Entropy-based Active Learning for Fair Brain Segmentation

2026-05-03 · Ghazal Danaee, Mélanie Gaillochet, Christian Desrosiers, Herve Lombaert 외 arxiv

Active learning (AL) has emerged as a crucial strategy for reducing the prohibitive costs associated with medical image segmentation. However, standard uncertainty-based AL methods typically focus on maximizing performan…

Medical Image SegmentationBrain SegmentationActive Learning

Exploring Structure-Wise Uncertainty for 3D Medical Image Segmentation

2022-11-01 · Anton Vasiliuk, Daria Frolova, Mikhail Belyaev, Boris Shirokikh

When applying a Deep Learning model to medical images, it is crucial to estimate the model uncertainty. Voxel-wise uncertainty is a useful visual marker for human experts and could be used to improve the model's voxel-wi…

Image SegmentationMedical Image SegmentationOut of Distribution (OOD) DetectionSegmentation+2