SOTAVerified

Self Meta Pseudo Labels: Meta Pseudo Labels Without The Teacher

2022-12-27Unverified0· sign in to hype

Kei-Sing Ng, Qingchen Wang

Unverified — Be the first to reproduce this paper.

Reproduce

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.

Tasks

Benchmark Results

DatasetModelMetricClaimedVerifiedStatus
cifar-100, 10000 LabelsSMPL (WRN-28-8)Percentage error21.68Unverified
CIFAR-10, 4000 LabelsSelf Meta Pseudo LabelsPercentage error4.09Unverified

Reproductions