paper-with-me

Papers

PSPU: Enhanced Positive and Unlabeled Learning by Leveraging Pseudo Supervision

2024-07-09 · Chengjie Wang, Chengming Xu, Zhenye Gan, Jianlong Hu, Wenbing Zhu, Lizhuag Ma

Positive and Unlabeled (PU) learning, a binary classification model trained with only positive and unlabeled data, generally suffers from overfitted risk estimation due to inconsistent data distributions. To address this, we introduce a pseudo-supervised PU learning framework (PSPU), in which we train the PU model first, use it to gather confident samples for the pseudo supervision, and then apply these supervision to correct the PU model's weights by leveraging non-PU objectives. We also incorporate an additional consistency loss to mitigate noisy sample effects. Our PSPU outperforms recent PU learning methods significantly on MNIST, CIFAR-10, CIFAR-100 in both balanced and imbalanced settings, and enjoys competitive performance on MVTecAD for industrial anomaly detection.

📄 PDF Abstract BibTeX arXiv:2407.06698

Code (0)

등록된 구현이 없습니다.

Tasks

Anomaly DetectionBinary Classification

Similar Papers 제목 키워드 기반

Deep Positive Unlabeled Learning with a Sequential Bias

2021-01-01 · Walter Gerych, Thomas Hartvigsen, Luke Buquicchio, Kavin Chandrasekaran 외

For many domains, from video stream analytics to human activity recognition, only weakly-labeled datasets are available. Worse yet, the given labels are often assigned sequentially, resulting in sequential bias. Current …

Activity RecognitionHuman Activity Recognition

CLAF: Contrastive Learning with Augmented Features for Imbalanced Semi-Supervised Learning

2023-12-15 · Bowen Tao, Lan Li, Xin-Chun Li, De-Chuan Zhan

Due to the advantages of leveraging unlabeled data and learning meaningful representations, semi-supervised learning and contrastive learning have been progressively combined to achieve better performances in popular app…

Contrastive Learningimage-classificationImage Classification

Pyramid U-Network for Skeleton Extraction From Shape Points

2019-06-17 · IEEE 2019 CVPR Workshop 2019 6 · Rowel Atienza

The knowledge about the skeleton of a given geometric shape has many practical applications such as shape animation, shape comparison, shape recognition, and estimating structural strength. Skeleton extraction becomes a …

Adaptive Pseudo Label Selection for Individual Unlabeled Data by Positive and Unlabeled Learning

2025-08-11 · Takehiro Yamane, Itaru Tsuge, Susumu Saito, Ryoma Bise arxiv

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 lea…

Medical Image SegmentationBinary Classification

TrajSSL: Trajectory-Enhanced Semi-Supervised 3D Object Detection

2024-09-17 · Philip Jacobson, Yichen Xie, Mingyu Ding, Chenfeng Xu 외

Semi-supervised 3D object detection is a common strategy employed to circumvent the challenge of manually labeling large-scale autonomous driving perception datasets. Pseudo-labeling approaches to semi-supervised learnin…

3D Object DetectionAutonomous DrivingMotion ForecastingObject+3