Self Meta Pseudo Labels: Meta Pseudo Labels Without The Teacher
This is an incremental improvement for researchers and practitioners in semi-supervised learning, addressing memory constraints without sacrificing performance.
The paper tackles the memory inefficiency of Meta Pseudo Labels in semi-supervised learning by proposing Self Meta Pseudo Labels, which uses a single model for both pseudo-label generation and classification, achieving similar performance while drastically reducing memory usage.
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.