Methods › General › Semi-Supervised Learning Methods › FixMatch
FixMatch
Introduced by Kihyuk Sohn et al. in FixMatch: Simplifying Semi-Supervised Learning with Consistency and Confidence
archive 2025-07-28 Description, source and code snippet are the archive's method entry.
FixMatch is an algorithm that first generates pseudo-labels using the model's predictions on weakly-augmented unlabeled images. For a given image, the pseudo-label is only retained if the model produces a high-confidence prediction. The model is then trained to predict the pseudo-label when fed a strongly-augmented version of the same image.
Description from: FixMatch: Simplifying Semi-Supervised Learning with Consistency and Confidence
Image credit: FixMatch: Simplifying Semi-Supervised Learning with Consistency and Confidence
In Syntology repository known, no verified implementation (declared_code; repositories: 5 listed of 26 in the graph, strongest link: official). This answer is about arXiv:2001.07685, the paper the archive credits with this method.
Origin paper of this answer, arXiv:2001.07685 (its page on this site · its page on Syntology): Syntology's run record for its harvested code, 53 ran (of which 13 constructed an object rather than computing a result; 25 with no instrument failure: 3 honoured, 2 violated, 20 with no contract checked; 28 where Syntology's instrument failed) · 21 unverified (of 74 harvested samples) · 17 pointer-only (licence). The instrument figure counts failures of Syntology's instrument, not of the code. Ran means executed on a synthesized input, not that the code is correct.
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: 85 · with a code link: 44 · where Syntology ran a sample: 19 (15 with a run with no instrument failure, 4 where every run was a failure of Syntology's instrument) Syntology
Show: all tagged papersonly where code ran (19 of 85 tagged: 15 with a run with no instrument failure, 4 where every run was a failure of Syntology's instrument)
Page 1 of 1: papers 1 to 85 of 85, 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.
-
AnomalyMatch: Discovering Rare Objects of Interest with Semi-supervised and Active Learning 6 May 2025 · 1 repository · arXiv:2505.03509
-
Towards Micro-Action Recognition with Limited Annotations: An Asynchronous Pseudo Labeling and Training Approach 10 Apr 2025 · 0 repositories · arXiv:2504.07785
-
Feature Modulation for Semi-Supervised Domain Generalization without Domain Labels 26 Mar 2025 · 0 repositories · arXiv:2503.20897
-
Uncertainty-aware Long-tailed Weights Model the Utility of Pseudo-labels for Semi-supervised Learning 13 Mar 2025 · 0 repositories · arXiv:2503.09974
-
Semi-Supervised Learning for Dose Prediction in Targeted Radionuclide: A Synthetic Data Study 7 Mar 2025 · 0 repositories · arXiv:2503.05367
-
Enhancing Deep Learning Model Robustness through Metamorphic Re-Training 2 Dec 2024 · 0 repositories · arXiv:2412.01958
-
RankUp: Boosting Semi-Supervised Regression with an Auxiliary Ranking Classifier 29 Oct 2024 · 1 repository · arXiv:2410.22124Syntology official (archive's flag): 9 ran · 9 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 1 honoured, 0 violated, 3 with no contract checked; 5 where Syntology's instrument failed) · 0 unverified (of 9 harvested samples) · 4 pointer-only (licence)
-
SemSim: Revisiting Weak-to-Strong Consistency from a Semantic Similarity Perspective for Semi-supervised Medical Image Segmentation 17 Oct 2024 · 0 repositories · arXiv:2410.13486
-
Towards Understanding Why FixMatch Generalizes Better Than Supervised Learning 15 Oct 2024 · 0 repositories · arXiv:2410.11206
-
Unsupervised Domain Adaption Harnessing Vision-Language Pre-training 5 Aug 2024 · 1 repository · arXiv:2408.02192Syntology official (archive's flag): 6 ran · 6 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 1 violated, 0 with no contract checked; 5 where Syntology's instrument failed) · 7 unverified (of 13 harvested samples) · 5 pointer-only (licence)
-
Smooth Pseudo-Labeling 23 May 2024 · 0 repositories · arXiv:2405.14313
-
SemiCD-VL: Visual-Language Model Guidance Makes Better Semi-supervised Change Detector 8 May 2024 · 2 repositories · arXiv:2405.04788
-
Unsupervised Domain Adaption Harnessing Vision-Language Pre-training 19 Apr 2024 · 1 repository
-
A Channel-ensemble Approach: Unbiased and Low-variance Pseudo-labels is Critical for Semi-supervised Classification 27 Mar 2024 · 0 repositories · arXiv:2403.18407
-
Semi-supervised Medical Image Segmentation Method Based on Cross-pseudo Labeling Leveraging Strong and Weak Data Augmentation Strategies 17 Feb 2024 · 1 repository · arXiv:2402.11273
-
Semi-Supervised Semantic Segmentation using Redesigned Self-Training for White Blood Cells 14 Jan 2024 · 0 repositories · arXiv:2401.07278
-
Uncertainty-aware Sampling for Long-tailed Semi-supervised Learning 9 Jan 2024 · 1 repository · arXiv:2401.04435
-
Debiased Learning for Remote Sensing Data 24 Dec 2023 · 0 repositories · arXiv:2312.15393
-
Semi-supervised Semantic Segmentation Meets Masked Modeling:Fine-grained Locality Learning Matters in Consistency Regularization 14 Dec 2023 · 0 repositories · arXiv:2312.08631
-
Generating Unbiased Pseudo-labels via a Theoretically Guaranteed Chebyshev Constraint to Unify Semi-supervised Classification and Regression 3 Nov 2023 · 1 repository · arXiv:2311.01782
-
SemiGPC: Distribution-Aware Label Refinement for Imbalanced Semi-Supervised Learning Using Gaussian Processes 3 Nov 2023 · 0 repositories · arXiv:2311.01646
-
On Training Implicit Meta-Learning With Applications to Inductive Weighing in Consistency Regularization 28 Oct 2023 · 0 repositories · arXiv:2310.18741
-
KD-FixMatch: Knowledge Distillation Siamese Neural Networks 11 Sep 2023 · 0 repositories · arXiv:2309.05826
-
Enhancing Sample Utilization through Sample Adaptive Augmentation in Semi-Supervised Learning 7 Sep 2023 · 1 repository · arXiv:2309.03598Syntology official (archive's flag): 4 ran · 4 ran (of which 1 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 3 where Syntology's instrument failed) · 1 unverified (of 5 harvested samples) · 5 pointer-only (licence)
-
Fast FixMatch: Faster Semi-Supervised Learning with Curriculum Batch Size 7 Sep 2023 · 0 repositories · arXiv:2309.03469
-
Boosting Semi-Supervised Learning by bridging high and low-confidence predictions 15 Aug 2023 · 0 repositories · arXiv:2308.07509
-
SegMatch: A semi-supervised learning method for surgical instrument segmentation 9 Aug 2023 · 0 repositories · arXiv:2308.05232
-
Exploring the Boundaries of Semi-Supervised Facial Expression Recognition using In-Distribution, Out-of-Distribution, and Unconstrained Data 2 Jun 2023 · 1 repository · arXiv:2306.01229
-
RelationMatch: Matching In-batch Relationships for Semi-supervised Learning 17 May 2023 · 1 repository · arXiv:2305.10397Syntology 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, 1 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified (of 1 harvested sample)
-
Distilling from Similar Tasks for Transfer Learning on a Budget 24 Apr 2023 · 1 repository · arXiv:2304.12314
-
Boosting Semi-Supervised Learning by Exploiting All Unlabeled Data 20 Mar 2023 · 1 repository · arXiv:2303.11066Syntology official (archive's flag): 6 ran · 6 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 1 violated, 5 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified (of 6 harvested samples)
-
When does the student surpass the teacher? Federated Semi-supervised Learning with Teacher-Student EMA 24 Jan 2023 · 0 repositories · arXiv:2301.10114
-
CHMATCH: Contrastive Hierarchical Matching and Robust Adaptive Threshold Boosted Semi-Supervised Learning 1 Jan 2023 · 1 repository
-
HyperMatch: Noise-Tolerant Semi-Supervised Learning via Relaxed Contrastive Constraint 1 Jan 2023 · 0 repositories
-
Land Cover and Land Use Detection using Semi-Supervised Learning 21 Dec 2022 · 0 repositories · arXiv:2212.11211
-
Boosting Semi-Supervised Learning with Contrastive Complementary Labeling 13 Dec 2022 · 0 repositories · arXiv:2212.06643
-
Impact of Strategic Sampling and Supervision Policies on Semi-supervised Learning 27 Nov 2022 · 0 repositories · arXiv:2211.14912
-
Dense FixMatch: a simple semi-supervised learning method for pixel-wise prediction tasks 18 Oct 2022 · 1 repository · arXiv:2210.09919
-
Revisiting Weak-to-Strong Consistency in Semi-Supervised Semantic Segmentation 21 Aug 2022 · 1 repository · arXiv:2208.09910Syntology official (archive's flag): 7 ran · 7 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 5 where Syntology's instrument failed) · 2 unverified (of 9 harvested samples) · 6 pointer-only (licence)
-
USB: A Unified Semi-supervised Learning Benchmark for Classification 12 Aug 2022 · 5 repositories · arXiv:2208.07204Syntology community repositories only · 9 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 4 honoured, 0 violated, 0 with no contract checked; 5 where Syntology's instrument failed) · 0 unverified (of 9 harvested samples)
-
MultiMatch: Multi-task Learning for Semi-supervised Domain Generalization 11 Aug 2022 · 0 repositories · arXiv:2208.05853
-
Semi-supervised Vision Transformers at Scale 11 Aug 2022 · 1 repository · arXiv:2208.05688
-
Augmentation Learning for Semi-Supervised Classification 3 Aug 2022 · 0 repositories · arXiv:2208.01956
-
Analysis of Semi-Supervised Methods for Facial Expression Recognition 31 Jul 2022 · 2 repositories · arXiv:2208.00544
-
FixMatchSeg: Fixing FixMatch for Semi-Supervised Semantic Segmentation 31 Jul 2022 · 0 repositories · arXiv:2208.00400
-
Federated Semi-Supervised Learning with Prototypical Networks 27 May 2022 · 1 repository · arXiv:2205.13921
-
FisherMatch: Semi-Supervised Rotation Regression via Entropy-based Filtering 29 Mar 2022 · 0 repositories · arXiv:2203.15765
-
Class-Aware Contrastive Semi-Supervised Learning 4 Mar 2022 · 1 repository · arXiv:2203.02261Syntology official (archive's flag): 2 ran · 2 ran (of which 1 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified (of 3 harvested samples) · 3 pointer-only (licence)
-
CLS: Cross Labeling Supervision for Semi-Supervised Learning 17 Feb 2022 · 1 repository · arXiv:2202.08502
-
Debiased Self-Training for Semi-Supervised Learning 15 Feb 2022 · 2 repositories · arXiv:2202.07136
-
Debiased Learning from Naturally Imbalanced Pseudo-Labels 5 Jan 2022 · 1 repository · arXiv:2201.01490Syntology official (archive's flag): 1 ran · 1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified (of 1 harvested sample)
-
An analysis of over-sampling labeled data in semi-supervised learning with FixMatch 3 Jan 2022 · 1 repository · arXiv:2201.00604
-
Towards Discovering the Effectiveness of Moderately Confident Samples for Semi-Supervised Learning 1 Jan 2022 · 0 repositories
-
Barely-Supervised Learning: Semi-Supervised Learning with very few labeled images 22 Dec 2021 · 0 repositories · arXiv:2112.12004
-
Cross-Model Pseudo-Labeling for Semi-Supervised Action Recognition 17 Dec 2021 · 0 repositories · arXiv:2112.09690
-
OpenMatch: Open-Set Semi-supervised Learning with Open-set Consistency Regularization 1 Dec 2021 · 1 repository
-
Semi-Supervised Learning with Taxonomic Labels 23 Nov 2021 · 1 repository · arXiv:2111.11595Syntology official (archive's flag): 1 ran · 1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified (of 1 harvested sample) · 1 pointer-only (licence)
-
Evaluating Self and Semi-Supervised Methods for Remote Sensing Segmentation Tasks 19 Nov 2021 · 0 repositories · arXiv:2111.10079
-
HIERMATCH: Leveraging Label Hierarchies for Improving Semi-Supervised Learning 30 Oct 2021 · 1 repository · arXiv:2111.00164
-
FlexMatch: Boosting Semi-Supervised Learning with Curriculum Pseudo Labeling 15 Oct 2021 · 2 repositories · arXiv:2110.08263Syntology official (archive's flag): 2 ran · 4 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 1 violated, 0 with no contract checked; 3 where Syntology's instrument failed) · 2 unverified (of 6 harvested samples)
-
ActiveMatch: End-to-end Semi-supervised Active Representation Learning 6 Oct 2021 · 0 repositories · arXiv:2110.02521
-
Unsupervised Selective Labeling for More Effective Semi-Supervised Learning 6 Oct 2021 · 1 repository · arXiv:2110.03006Syntology official (archive's flag): 7 ran · 7 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 1 honoured, 0 violated, 4 with no contract checked; 2 where Syntology's instrument failed) · 1 unverified (of 8 harvested samples) · 2 pointer-only (licence)
-
Spatial Ensemble: a Novel Model Smoothing Mechanism for Student-Teacher Framework 4 Oct 2021 · 1 repository · arXiv:2110.01253
-
Holistic Semi-Supervised Approaches for EEG Representation Learning 24 Sep 2021 · 0 repositories · arXiv:2109.11732
-
OpenCoS: Contrastive Semi-supervised Learning for Handling Open-set Unlabeled Data 29 Jun 2021 · 1 repository · arXiv:2107.08943Syntology official (archive's flag): 2 ran · 2 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified (of 2 harvested samples) · 2 pointer-only (licence)
-
RETRIEVE: Coreset Selection for Efficient and Robust Semi-Supervised Learning 14 Jun 2021 · 2 repositories · arXiv:2106.07760
-
Semi-Supervised Domain Generalization with Stochastic StyleMatch 1 Jun 2021 · 2 repositories · arXiv:2106.00592Syntology official (archive's flag): 4 ran · 4 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; 3 where Syntology's instrument failed) · 0 unverified (of 4 harvested samples)
-
OpenMatch: Open-set Consistency Regularization for Semi-supervised Learning with Outliers 28 May 2021 · 1 repository · arXiv:2105.14148Syntology official (archive's flag): 15 ran · 15 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 1 violated, 5 with no contract checked; 9 where Syntology's instrument failed) · 4 unverified (of 19 harvested samples) · 7 pointer-only (licence)
-
Adaptive Consistency Regularization for Semi-Supervised Transfer Learning 3 Mar 2021 · 1 repository · arXiv:2103.02193Syntology official (archive's flag): 3 ran · 3 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; 2 where Syntology's instrument failed) · 0 unverified (of 3 harvested samples)
-
Sinkhorn Label Allocation: Semi-Supervised Classification via Annealed Self-Training 17 Feb 2021 · 1 repository · arXiv:2102.08622Syntology official (archive's flag): 2 ran · 2 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 1 honoured, 1 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified (of 2 harvested samples)
-
Comparison of semi-supervised deep learning algorithms for audio classification 16 Feb 2021 · 1 repository · arXiv:2102.08183
-
SelfMatch: Combining Contrastive Self-Supervision and Consistency for Semi-Supervised Learning 16 Jan 2021 · 0 repositories · arXiv:2101.06480
-
3DIoUMatch: Leveraging IoU Prediction for Semi-Supervised 3D Object Detection 8 Dec 2020 · 2 repositories · arXiv:2012.04355
-
[Re] Reimplementation of FixMatch and Investigation on Noisy (Pseudo) Labels and Confirmation Errors of FixMatch 6 Dec 2020 · 1 repository
-
Assessing Post-Disaster Damage from Satellite Imagery using Semi-Supervised Learning Techniques 24 Nov 2020 · 0 repositories · arXiv:2011.14004
-
AlphaMatch: Improving Consistency for Semi-supervised Learning with Alpha-divergence 23 Nov 2020 · 0 repositories · arXiv:2011.11779
-
CoMatch: Semi-supervised Learning with Contrastive Graph Regularization 23 Nov 2020 · 3 repositories · arXiv:2011.11183Syntology official (archive's flag): 2 ran · 2 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 1 unverified (of 3 harvested samples)
-
Matching the Clinical Reality: Accurate OCT-Based Diagnosis From Few Labels 23 Oct 2020 · 1 repository · arXiv:2010.12316
-
LiDAM: Semi-Supervised Learning with Localized Domain Adaptation and Iterative Matching 13 Oct 2020 · 0 repositories · arXiv:2010.06668
-
Learning Calibrated Uncertainties for Domain Shift: A Distributionally Robust Learning Approach 8 Oct 2020 · 0 repositories · arXiv:2010.05784
-
Semi-supervised learning objectives as log-likelihoods in a generative model of data curation 13 Aug 2020 · 0 repositories · arXiv:2008.05913
-
Semi-Supervised Learning with Data Augmentation for End-to-End ASR 27 Jul 2020 · 0 repositories · arXiv:2007.13876
-
Empirical Perspectives on One-Shot Semi-supervised Learning 8 Apr 2020 · 0 repositories · arXiv:2004.04141
-
FixMatch: Simplifying Semi-Supervised Learning with Consistency and Confidence 21 Jan 2020 · 26 repositories · arXiv:2001.07685Syntology community repositories only · 53 ran (of which 13 constructed an object rather than computing a result; 25 with no instrument failure: 3 honoured, 2 violated, 20 with no contract checked; 28 where Syntology's instrument failed) · 21 unverified (of 74 harvested samples) · 17 pointer-only (licence)
-
FixMatch: Simplifying Semi-Supervised Learning with Consistency and Confidence 21 Jan 2020 · 1 repository
Tasks archive 2025-07-28
20 shown of 85 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