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.
@article{arxiv.2212.13420,
title = {Self Meta Pseudo Labels: Meta Pseudo Labels Without The Teacher},
author = {Kei-Sing Ng and Qingchen Wang},
journal= {arXiv preprint arXiv:2212.13420},
year = {2022}
}