按年被提到
20202020 · 3 次2026
视觉、语音与图像生成›视觉语言与自监督表征·arXiv:2001.07685 · cs.LG

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 · 2020
开始阅读 ↗PDFalphaXiv 讨论
被提及 · 3 人首次 2020-01-23 · 最近 2020-04-03
3不同的人
2活跃月份
2讨论串
2,918被引(OpenAlex)
arXiv 摘要(候选层不写导读)

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.

候选层:至少 2 个不同的人、在 2 个不同月份提到过,还没到主书架的 3 人 3 个月。没有做立场标注,所以只写“被提及”。

HN 书评

推荐在前,同类按时间 · 每篇最多保留 20 条,统计用全部提及
评论colincooke · 2020-04

“This is a blog not a paper, it seems you wouldn't like the source material: https://arxiv.org/pdf/2001.07685.pdf But you are correct! This way of showing off your work is much nicer than what ends up in the paper. The blog representation is a good opportunity to show off the results of the paper on a higher level. However, the "mathy" paper is still impo…”

Illustrated FixMatch for semi-supervised learning原评论 ↗
评论amitness · 2020-04

“Hi, Wanted to clarify that this is the summary article of the paper. I wrote it to help out people who might not have the math rigor and research background to understand research papers but would benefit from an intuitive explanation. The actual paper is available here: https://arxiv.org/abs/2001.07685”

Illustrated FixMatch for semi-supervised learning原评论 ↗
被提交为 story · 1 次