FixMatch: Simplifying Semi-Supervised Learning with Consistency and Confidence
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 strongly-augmented 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 (26)
Tasks
Image ClassificationPseudo LabelSemi-Supervised Image ClassificationMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
FixMatch: Simplifying Semi-Supervised Learning with Consistency and Confidence
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: cons…
Image ClassificationPseudo LabelAlphaMatch: Improving Consistency for Semi-supervised Learning with Alpha-divergence
Semi-supervised learning (SSL) is a key approach toward more data-efficient machine learning by jointly leverage both labeled and unlabeled data. We propose AlphaMatch, an efficient SSL method that leverages data augment…
[Re] Reimplementation of FixMatch and Investigation on Noisy (Pseudo) Labels and Confirmation Errors of FixMatch
FixMatch is a semi-supervised learning method, which achieves comparable results with fully supervised learning by leveraging a limited number of labeled data (pseudo labelling technique) and taking a good use of the unl…
Semi-Supervised Image ClassificationDense FixMatch: a simple semi-supervised learning method for pixel-wise prediction tasks
We propose Dense FixMatch, a simple method for online semi-supervised learning of dense and structured prediction tasks combining pseudo-labeling and consistency regularization via strong data augmentation. We enable the…
Data Augmentationimage-classificationSemantic SegmentationSemi-Supervised Semantic SegmentationOpenMatch: Open-set Consistency Regularization for Semi-supervised Learning with Outliers
Semi-supervised learning (SSL) is an effective means to leverage unlabeled data to improve a model's performance. Typical SSL methods like FixMatch assume that labeled and unlabeled data share the same label space. Howev…
Novelty DetectionOutlier Detection