Methods › General › Semi-Supervised Learning Methods › Meta Pseudo Labels

Meta Pseudo Labels

5 papers tagged archive 2025-07-28

Introduced by Hieu Pham et al. in Meta Pseudo Labels

archive 2025-07-28 Description, source and code snippet are the archive's method entry.

Meta Pseudo Labels is a semi-supervised learning method that uses a teacher network to generate pseudo labels on unlabeled data to teach a student network. The teacher receives feedback from the student to inform the teacher to generate better pseudo labels. This feedback signal is used as a reward to train the teacher throughout the course of the student’s learning.

Paper Source

Papers archive 2025-07-28

5 shown of 5, newest first. Repository counts are the archive's code-links table. A Syntology line states what Syntology ran from that paper's harvested code; it is per sample and not a correctness claim.

The Efficiency of Pre-training with Objective Masking in Pseudo Labeling for Semi-Supervised Text Classification
10 May 2025 · 0 repositories · arXiv:2505.06624
Meta Co-Training: Two Views are Better than One
29 Nov 2023 · 1 repository · arXiv:2311.18083

Syntology ran 1 of 1 samples · 0 unverified · 1 pointer-only (licence)
Self Meta Pseudo Labels: Meta Pseudo Labels Without The Teacher
27 Dec 2022 · 0 repositories · arXiv:2212.13420
Dense Interspecies Face Embedding
28 Nov 2022 · 1 repository
Meta Pseudo Labels
23 Mar 2020 · 9 repositories · arXiv:2003.10580

Syntology ran 5 of 14 samples · 9 unverified

Tasks archive 2025-07-28

13 tasks the archive attaches to papers tagged with this method, by distinct papers. A task without a page in the catalog is plain text.

Task	Papers
Semi-Supervised Image Classification	3
Image Classification	2
Fine-Grained Image Classification	1
Image Manipulation	1
Interspecies Facial Keypoint Transfer	1
Keypoint Detection	1
Knowledge Distillation	1
Meta-Learning	1
Semi-Supervised Text Classification	1
Text Classification	1
Unsupervised Pre-training	1
image-classification	1
text-classification	1

Usage over time archive 2025-07-28

Papers per year the archive tags with this method, by the paper's archive date (5 dated). Bars are counts, not a trend claim.

Components: the archive holds no method-to-method composition, so PwC's Components table cannot be rebuilt; the Papers list carries no Results column for the same reason (the archive does not join its leaderboard rows to method tags).

Categories archive 2025-07-28

Semi-Supervised Learning Methods

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections