About This Document
- sl:arxiv_author :
- sl:arxiv_firstAuthor : Kihyuk Sohn
- sl:arxiv_num : 2001.07685
- sl:arxiv_published : 2020-01-21T18:32:27Z
- sl:arxiv_summary : 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.@en
- sl:arxiv_title : FixMatch: Simplifying Semi-Supervised Learning with Consistency and Confidence@en
- sl:arxiv_updated : 2020-01-21T18:32:27Z
- sl:bookmarkOf : https://arxiv.org/abs/2001.07685
- sl:creationDate : 2020-01-22
- sl:creationTime : 2020-01-22T18:11:37Z
Documents with similar tags (experimental)