Self Meta Pseudo Labels: Meta Pseudo Labels Without The Teacher
Kei-Sing Ng, Qingchen Wang
2022-12-27Semi-Supervised Image Classification
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
| Task | Dataset | Metric | Value | Model |
|---|---|---|---|---|
| Image Classification | CIFAR-10, 4000 Labels | Percentage error | 4.09 | Self Meta Pseudo Labels |
| Image Classification | cifar-100, 10000 Labels | Percentage error | 21.68 | SMPL (WRN-28-8) |
| Semi-Supervised Image Classification | CIFAR-10, 4000 Labels | Percentage error | 4.09 | Self Meta Pseudo Labels |
| Semi-Supervised Image Classification | cifar-100, 10000 Labels | Percentage error | 21.68 | SMPL (WRN-28-8) |
Related Papers
ViTSGMM: A Robust Semi-Supervised Image Recognition Network Using Sparse Labels2025-06-04Applications and Effect Evaluation of Generative Adversarial Networks in Semi-Supervised Learning2025-05-26Simple Semi-supervised Knowledge Distillation from Vision-Language Models via $\mathbf{\texttt{D}}$ual-$\mathbf{\texttt{H}}$ead $\mathbf{\texttt{O}}$ptimization2025-05-12Weakly Semi-supervised Whole Slide Image Classification by Two-level Cross Consistency Supervision2025-04-16Diff-SySC: An Approach Using Diffusion Models for Semi-Supervised Image Classification2025-02-25SynCo: Synthetic Hard Negatives in Contrastive Learning for Better Unsupervised Visual Representations2024-10-03Self Adaptive Threshold Pseudo-labeling and Unreliable Sample Contrastive Loss for Semi-supervised Image Classification2024-07-04A Method of Moments Embedding Constraint and its Application to Semi-Supervised Learning2024-04-27