Papers › FixMatch: Simplifying Semi-Supervised Learning with Consistency and Confidence

FixMatch: Simplifying Semi-Supervised Learning with Consistency and Confidence

21 Jan 2020archive 2025-07-28

Kihyuk Sohn∗ David Berthelot∗ Chun-Liang Li Zizhao Zhang Nicholas Carlini Ekin D. Cubuk Alex Kurakin Han Zhang Colin Raffel

Semi-supervised learning (SSL) provides an effective means of leveraging unlabeled data to improve a model’s performance. In this paper, we demonstrate the power of a simple combination of two common SSL methods: consistency regularization and pseudo-labeling. Our algorithm, FixMatch, 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 stronglyaugmented version of the same image. Despite its simplicity, we show that FixMatch achieves state-of-the-art performance across a variety of standard semi-supervised learning benchmarks, including 94.93% accuracy on CIFAR-10 with 250 labels and 88.61% accuracy with 40 – just 4 labels per class. Since FixMatch bears many similarities to existing SSL methods that achieve worse performance, we carry out an extensive ablation study to tease apart the experimental factors that are most important to FixMatch’s success. We make our code available at https: //github.com/google-research/fixmatch.

PaperPDFCode

Code

google-research/fixmatch mentioned in papertfApache-2.0 report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

Image ClassificationPseudo Label

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Image Classification STL-10 FixMatch (CTA) Percentage correct 94.83 #19 of 117 Archive leaderboard report
Image Classification STL-10 ReMixMatch Percentage correct 94.77 #20 of 117 Archive leaderboard report
Image Classification STL-10 UDA Percentage correct 92.34 #28 of 117 Archive leaderboard report
Image Classification STL-10 FixMatch (RA) Percentage correct 92.02 #30 of 117 Archive leaderboard report
Image Classification STL-10 MixMatch Percentage correct 89.59 #37 of 117 Archive leaderboard report
Image Classification STL-10 Mean Teacher Percentage correct 78.57 #66 of 117 Archive leaderboard report
Image Classification STL-10 Π-Model Percentage correct 73.77 #82 of 117 Archive leaderboard report
Image Classification STL-10 Pseudo-Labeling Percentage correct 72.01 #85 of 117 Archive leaderboard report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

Methods

FixMatch

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