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.
ReproduceAbstract
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
| Dataset | Model | Metric | Claimed | Verified | Status |
|---|---|---|---|---|---|
| cifar-100, 10000 Labels | SMPL (WRN-28-8) | Percentage error | 21.68 | — | Unverified |
| CIFAR-10, 4000 Labels | Self Meta Pseudo Labels | Percentage error | 4.09 | — | Unverified |