Methods › General › Semi-Supervised Learning Methods › Noisy Student
Noisy Student
archive 2025-07-28 Description, source and code snippet are the archive's method entry.
Noisy Student Training is a semi-supervised learning approach. It extends the idea of self-training and distillation with the use of equal-or-larger student models and noise added to the student during learning. It has three main steps:
- train a teacher model on labeled images
- use the teacher to generate pseudo labels on unlabeled images
- train a student model on the combination of labeled images and pseudo labeled images.
The algorithm is iterated a few times by treating the student as a teacher to relabel the unlabeled data and training a new student.
Noisy Student Training seeks to improve on self-training and distillation in two ways. First, it makes the student larger than, or at least equal to, the teacher so the student can better learn from a larger dataset. Second, it adds noise to the student so the noised student is forced to learn harder from the pseudo labels. To noise the student, it uses input noise such as RandAugment data augmentation, and model noise such as dropout and stochastic depth during training.
In Syntology name not resolved (unknown_name). The lookup matched no method, paper or venue by this name; that asserts nothing about whether code exists.
Near matches the lookup lists, each a different name: Noisy Student Training; NOPD (Noisy Student On-Policy Self-Distillation); IAG-Student; Noisy Nodes; Dual Student; Noisy Alignment; Noisy but Valid; PLL student model.
Syntology's have check for this name (free, it answers coverage only), read 2026-10-05; ask it again live. A level is the served verification level of that one answer; nothing here is summed across methods.
Papers archive 2025-07-28
archive papers tagged: 38 · with a code link: 13 · where Syntology ran a sample: 4 (4 with a run with no instrument failure, 0 where every run was a failure of Syntology's instrument) Syntology
Show: all tagged papersonly where code ran (4 of 38 tagged: 4 with a run with no instrument failure, 0 where every run was a failure of Syntology's instrument)
Page 1 of 1: papers 1 to 38 of 38, newest first by the archive's date (ties by slug), in archive order.
Repository counts are the archive's code-links table. A Syntology line states what Syntology ran from that paper's harvested code, as “N ran (of which C constructed an object rather than computing a result; K with no instrument failure: H honoured, V violated, P with no contract checked; I where Syntology's instrument failed) · U unverified”; the instrument figure counts failures of Syntology's instrument, not of the code. It is per sample and not a correctness claim. When the archive marks a repository official for the paper, the line starts with that repository's state (the archive's flag, not a verdict on who wrote the code; “community repositories only” when every sample that ran came from a community repository, “official: no sample here; runs from other or unrecorded repositories” when some came from a repository the paper names or has in its text, or from none recorded); hover it for the repositories the samples that ran came from.
-
SST: Self-training with Self-adaptive Thresholding for Semi-supervised Learning 31 May 2025 · 0 repositories · arXiv:2506.00467
-
ZIPA: A family of efficient models for multilingual phone recognition 29 May 2025 · 1 repository · arXiv:2505.23170Syntology official (archive's flag): 1 ran · 1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified (of 1 harvested sample)
-
HDC: Hierarchical Distillation for Multi-level Noisy Consistency in Semi-Supervised Fetal Ultrasound Segmentation 14 Apr 2025 · 0 repositories · arXiv:2504.09876
-
Improving noisy student training for low-resource languages in End-to-End ASR using CycleGAN and inter-domain losses 26 Jul 2024 · 0 repositories · arXiv:2407.21061
-
Semi-supervised Learning for Code-Switching ASR with Large Language Model Filter 5 Jul 2024 · 0 repositories · arXiv:2407.04219
-
GigaSpeech 2: An Evolving, Large-Scale and Multi-domain ASR Corpus for Low-Resource Languages with Automated Crawling, Transcription and Refinement 17 Jun 2024 · 2 repositories · arXiv:2406.11546Syntology official (archive's flag): 1 ran · 1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified (of 2 harvested samples)
-
Self-Train Before You Transcribe 17 Jun 2024 · 1 repository · arXiv:2406.12937
-
Conformer-1: Robust ASR via Large-Scale Semisupervised Bootstrapping 10 Apr 2024 · 0 repositories · arXiv:2404.07341
-
On the Effect of Image Resolution on Semantic Segmentation 8 Feb 2024 · 0 repositories · arXiv:2402.05398
-
Efficient Adapter Finetuning for Tail Languages in Streaming Multilingual ASR 17 Jan 2024 · 0 repositories · arXiv:2401.08992
-
Self-supervised Reflective Learning through Self-distillation and Online Clustering for Speaker Representation Learning 3 Jan 2024 · 0 repositories · arXiv:2401.01473
-
Self-Transriber: Few-shot Lyrics Transcription with Self-training 18 Nov 2022 · 0 repositories · arXiv:2211.10152
-
Comparison of Soft and Hard Target RNN-T Distillation for Large-scale ASR 11 Oct 2022 · 0 repositories · arXiv:2210.05793
-
Progress and limitations of deep networks to recognize objects in unusual poses 16 Jul 2022 · 1 repository · arXiv:2207.08034
-
FedNST: Federated Noisy Student Training for Automatic Speech Recognition 6 Jun 2022 · 0 repositories · arXiv:2206.02797
-
Conformer and Blind Noisy Students for Improved Image Quality Assessment 27 Apr 2022 · 1 repository · arXiv:2204.12819
-
Pseudo-Label Transfer from Frame-Level to Note-Level in a Teacher-Student Framework for Singing Transcription from Polyphonic Music 25 Mar 2022 · 1 repository · arXiv:2203.13422
-
Pseudo Label Is Better Than Human Label 22 Mar 2022 · 0 repositories · arXiv:2203.12668
-
Occlusion-Aware Self-Supervised Monocular 6D Object Pose Estimation 19 Mar 2022 · 1 repository · arXiv:2203.10339
-
Semi-supervised music emotion recognition using noisy student training and harmonic pitch class profiles 1 Dec 2021 · 1 repository · arXiv:2112.00702
-
Using Contrastive Learning and Pseudolabels to learn representations for Retail Product Image Classification 7 Oct 2021 · 0 repositories · arXiv:2110.03639
-
Perturb, Predict & Paraphrase: Semi-Supervised Learning using Noisy Student for Image Captioning 19 Aug 2021 · 1 repository
-
STAR: Noisy Semi-Supervised Transfer Learning for Visual Classification 18 Aug 2021 · 0 repositories · arXiv:2108.08362
-
CASPIANET++: A Multidimensional Channel-Spatial Asymmetric Attention Network with Noisy Student Curriculum Learning Paradigm for Brain Tumor Segmentation 8 Jul 2021 · 0 repositories · arXiv:2107.04099
-
Self-training with noisy student model and semi-supervised loss function for dcase 2021 challenge task 4 6 Jul 2021 · 0 repositories · arXiv:2107.02569
-
Semi-supervised Learning for Dense Object Detection in Retail Scenes 5 Jul 2021 · 0 repositories · arXiv:2107.02114
-
Predicting Students’ Difficulties From a Piece of Code 3 Jun 2021 · 0 repositories
-
Deep learning for detecting pulmonary tuberculosis via chest radiography: an international study across 10 countries 16 May 2021 · 0 repositories · arXiv:2105.07540
-
Semi-supervised learning for generalizable intracranial hemorrhage detection and segmentation 3 May 2021 · 0 repositories · arXiv:2105.00582
-
A new semi-supervised self-training method for lung cancer prediction 17 Dec 2020 · 0 repositories · arXiv:2012.09472
-
PGSG at SemEval-2020 Task 12: BERT-LSTM with Tweets' Pretrained Model and Noisy Student Training Method 1 Dec 2020 · 0 repositories
-
Semi-Supervised Noisy Student Pre-training on EfficientNet Architectures for Plant Pathology Classification 1 Dec 2020 · 0 repositories · arXiv:2012.00332
-
Combining Self-Training and Self-Supervised Learning for Unsupervised Disfluency Detection 29 Oct 2020 · 1 repository · arXiv:2010.15360
-
Pushing the Limits of Semi-Supervised Learning for Automatic Speech Recognition 20 Oct 2020 · 1 repository · arXiv:2010.10504Syntology 2 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified (of 2 harvested samples) · 2 pointer-only (licence)
-
Noisy Student Training using Body Language Dataset Improves Facial Expression Recognition 6 Aug 2020 · 0 repositories · arXiv:2008.02655
-
Semi-Supervised Learning with Data Augmentation for End-to-End ASR 27 Jul 2020 · 0 repositories · arXiv:2007.13876
-
Improved Noisy Student Training for Automatic Speech Recognition 19 May 2020 · 1 repository · arXiv:2005.09629
-
Self-training with Noisy Student improves ImageNet classification 11 Nov 2019 · 13 repositories · arXiv:1911.04252Syntology official (archive's flag): 6 ran · 13 ran (of which 0 constructed an object rather than computing a result; 10 with no instrument failure: 2 honoured, 0 violated, 8 with no contract checked; 3 where Syntology's instrument failed) · 11 unverified (of 24 harvested samples) · 2 pointer-only (licence)
Tasks archive 2025-07-28
20 shown of 65 tasks the archive attaches to papers tagged with this method, by distinct papers. A task without a page in the catalog is plain text.
Usage over time archive 2025-07-28
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
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