FixMatch: Simplifying Semi-Supervised Learning with Consistency and Confidence
| dc.contributor.author | Sohn, Kihyuk | |
| dc.contributor.author | Berthelot, David | |
| dc.contributor.author | Li, Chun‑Liang | |
| dc.contributor.author | Zhang, Zizhao | |
| dc.contributor.author | Carlini, Nicholas | |
| dc.contributor.author | Cubuk, Ekin D | |
| dc.contributor.author | Kurakin, Alex | |
| dc.contributor.author | Zhang, Han | |
| dc.contributor.author | Raffel, Colin | |
| dc.date.accessioned | 2025-06-02T11:27:40Z | |
| dc.date.available | 2025-06-02T11:27:40Z | |
| dc.date.issued | 2020-01-21 | |
| dc.description | FixMatch는 최소한의 구성으로 준지도 학습을 수행하는 방법으로, 모델의 약한 증강 이미지 예측으로 가짜 레이블 생성 후 강한 증강 이미지 학습에 활용합니다 ©2020 Authors | |
| dc.description.abstract | 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 this https URL. | |
| dc.description.sponsorship | Google Research | |
| dc.identifier.uri | https://arxiv.org/abs/2001.07685 | |
| dc.identifier.uri | http://data.inu.ac.kr/handle/123456789/1946 | |
| dc.language.iso | en_US | |
| dc.publisher | arXiv | |
| dc.subject | FixMatch | |
| dc.subject | Semi-Supervised Learning | |
| dc.subject | Computer Vision | |
| dc.subject | SSL | |
| dc.subject | Consistency Regularization | |
| dc.subject | Image analysis | |
| dc.subject | Computer science | |
| dc.title | FixMatch: Simplifying Semi-Supervised Learning with Consistency and Confidence | |
| dc.title.alternative | FixMatch | |
| dc.type | Article |