PSPU: Enhanced Positive and Unlabeled Learning by Leveraging Pseudo Supervision
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.
Code (0)
등록된 구현이 없습니다.
Tasks
Anomaly DetectionBinary ClassificationSimilar Papers 제목 키워드 기반
Deep Positive Unlabeled Learning with a Sequential Bias
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 RecognitionCLAF: Contrastive Learning with Augmented Features for Imbalanced Semi-Supervised Learning
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 ClassificationPyramid U-Network for Skeleton Extraction From Shape Points
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
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 ClassificationTrajSSL: Trajectory-Enhanced Semi-Supervised 3D Object Detection
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