Saved in:
Bibliographic Details
Main Authors: Yamane, Takehiro, Tsuge, Itaru, Saito, Susumu, Bise, Ryoma
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2508.07548
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866912531349504000
author Yamane, Takehiro
Tsuge, Itaru
Saito, Susumu
Bise, Ryoma
author_facet Yamane, Takehiro
Tsuge, Itaru
Saito, Susumu
Bise, Ryoma
contents This paper proposes a novel pseudo-labeling method for medical image segmentation that can perform learning on ``individual images'' to select effective pseudo-labels. We introduce Positive and Unlabeled Learning (PU learning), which uses only positive and unlabeled data for binary classification problems, to obtain the appropriate metric for discriminating foreground and background regions on each unlabeled image. Our PU learning makes us easy to select pseudo-labels for various background regions. The experimental results show the effectiveness of our method.
format Preprint
id arxiv_https___arxiv_org_abs_2508_07548
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Adaptive Pseudo Label Selection for Individual Unlabeled Data by Positive and Unlabeled Learning
Yamane, Takehiro
Tsuge, Itaru
Saito, Susumu
Bise, Ryoma
Computer Vision and Pattern Recognition
This paper proposes a novel pseudo-labeling method for medical image segmentation that can perform learning on ``individual images'' to select effective pseudo-labels. We introduce Positive and Unlabeled Learning (PU learning), which uses only positive and unlabeled data for binary classification problems, to obtain the appropriate metric for discriminating foreground and background regions on each unlabeled image. Our PU learning makes us easy to select pseudo-labels for various background regions. The experimental results show the effectiveness of our method.
title Adaptive Pseudo Label Selection for Individual Unlabeled Data by Positive and Unlabeled Learning
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2508.07548