Papers › FixMatch: Simplifying Semi-Supervised Learning with Consistency and Confidence
FixMatch: Simplifying Semi-Supervised Learning with Consistency and Confidence
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.
Code
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
Results from the paper archive 2025-07-28
| Task | Dataset | Model | Metric | Value | Rank at snapshot | Leaderboard | Report |
|---|---|---|---|---|---|---|---|
| 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
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