REVIEW 2 cited by
Meta Pseudo Labels
Not yet reviewed by Pith; the record is open.
This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.
SPECIMEN: schema-true, not a live event
T0 review · schema-true
One-sentence machine reading of the paper's core claim.
pith:XXXXXXXX · record.json · timestamp
Signed reviews
read the original abstract
We present Meta Pseudo Labels, a semi-supervised learning method that achieves a new state-of-the-art top-1 accuracy of 90.2% on ImageNet, which is 1.6% better than the existing state-of-the-art. Like Pseudo Labels, Meta Pseudo Labels has a teacher network to generate pseudo labels on unlabeled data to teach a student network. However, unlike Pseudo Labels where the teacher is fixed, the teacher in Meta Pseudo Labels is constantly adapted by the feedback of the student's performance on the labeled dataset. As a result, the teacher generates better pseudo labels to teach the student. Our code will be available at https://github.com/google-research/google-research/tree/master/meta_pseudo_labels.
Forward citations
Cited by 2 Pith papers
-
UPL: Uncertainty-aware Pseudo-labeling for Imbalance Transductive Node Classification
The paper derives a per-class generalization bound for imbalanced transductive node classification and introduces UPL, a pseudo-labeling algorithm that filters minority-class pseudo-labels by entropy variance across e...
-
The Efficiency of Pre-training with Objective Masking in Pseudo Labeling for Semi-Supervised Text Classification
CformerM extends Cformer with LDA-based objective masking during pre-training and reports consistent, modest accuracy gains over Cformer and baselines across four text datasets.
Discussion (0). Continue with ORCID to comment.