Methods › General › Semi-Supervised Learning Methods › FixMatch

FixMatch

85 papers tagged archive 2025-07-28

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

PaperSource

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.

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.

TaskPapers
Pseudo Label20
Semi-Supervised Image Classification16
Image Classification8
Semantic Segmentation8
Contrastive Learning7
Representation Learning6
Segmentation6
image-classification6
Data Augmentation5
Semi-Supervised Semantic Segmentation5
Active Learning4
Classification4
Domain Adaptation4
Medical Image Segmentation4
Transfer Learning4
Domain Generalization3
Image Segmentation3
Semi-Supervised Domain Generalization3
Semi-supervised Medical Image Segmentation3
Unsupervised Domain Adaptation3

Usage over time archive 2025-07-28

Papers per year tagged with FixMatch: 2020 to 2025, peak 19 19 0 2020: 13 papers 2020 2021: 19 papers 2021 2022: 19 papers 2022 2023: 17 papers 2023 2024: 12 papers 2024 2025: 5 papers 2025
Papers per year the archive tags with this method, by the paper's archive date (85 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