Self Meta Pseudo Labels: Meta Pseudo Labels Without The Teacher

Kei-Sing Ng, Qingchen Wang

Abstract

We present Self Meta Pseudo Labels, a novel semi-supervised learning method similar to Meta Pseudo Labels but without the teacher model. We introduce a novel way to use a single model for both generating pseudo labels and classification, allowing us to store only one model in memory instead of two. Our method attains similar performance to the Meta Pseudo Labels method while drastically reducing memory usage.

Results

TaskDatasetMetricValueModel
Image ClassificationCIFAR-10, 4000 LabelsPercentage error4.09Self Meta Pseudo Labels
Image Classificationcifar-100, 10000 LabelsPercentage error21.68SMPL (WRN-28-8)
Semi-Supervised Image ClassificationCIFAR-10, 4000 LabelsPercentage error4.09Self Meta Pseudo Labels
Semi-Supervised Image Classificationcifar-100, 10000 LabelsPercentage error21.68SMPL (WRN-28-8)

Related Papers