TasksSotADatasetsPapersMethodsSubmitAbout
Papers With Code 2

A community resource for machine learning research: papers, code, benchmarks, and state-of-the-art results.

Explore

Notable BenchmarksAll SotADatasetsPapersMethods

Community

Submit ResultsAbout

Data sourced from the PWC Archive (CC-BY-SA 4.0). Built by the community, for the community.

Methods/FixMatch

FixMatch

GeneralIntroduced 200085 papers
Source Paper

Description

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

Papers Using This Method

AnomalyMatch: Discovering Rare Objects of Interest with Semi-supervised and Active Learning2025-05-06Towards Micro-Action Recognition with Limited Annotations: An Asynchronous Pseudo Labeling and Training Approach2025-04-10Feature Modulation for Semi-Supervised Domain Generalization without Domain Labels2025-03-26Uncertainty-aware Long-tailed Weights Model the Utility of Pseudo-labels for Semi-supervised Learning2025-03-13Semi-Supervised Learning for Dose Prediction in Targeted Radionuclide: A Synthetic Data Study2025-03-07Enhancing Deep Learning Model Robustness through Metamorphic Re-Training2024-12-02RankUp: Boosting Semi-Supervised Regression with an Auxiliary Ranking Classifier2024-10-29SemSim: Revisiting Weak-to-Strong Consistency from a Semantic Similarity Perspective for Semi-supervised Medical Image Segmentation2024-10-17Towards Understanding Why FixMatch Generalizes Better Than Supervised Learning2024-10-15Unsupervised Domain Adaption Harnessing Vision-Language Pre-training2024-08-05Smooth Pseudo-Labeling2024-05-23SemiCD-VL: Visual-Language Model Guidance Makes Better Semi-supervised Change Detector2024-05-08Unsupervised Domain Adaption Harnessing Vision-Language Pre-training2024-04-19A Channel-ensemble Approach: Unbiased and Low-variance Pseudo-labels is Critical for Semi-supervised Classification2024-03-27Semi-supervised Medical Image Segmentation Method Based on Cross-pseudo Labeling Leveraging Strong and Weak Data Augmentation Strategies2024-02-17Semi-Supervised Semantic Segmentation using Redesigned Self-Training for White Blood Cells2024-01-14Uncertainty-aware Sampling for Long-tailed Semi-supervised Learning2024-01-09Debiased Learning for Remote Sensing Data2023-12-24Semi-supervised Semantic Segmentation Meets Masked Modeling:Fine-grained Locality Learning Matters in Consistency Regularization2023-12-14Generating Unbiased Pseudo-labels via a Theoretically Guaranteed Chebyshev Constraint to Unify Semi-supervised Classification and Regression2023-11-03