paper-with-me

Papers

FixMatch: Simplifying Semi-Supervised Learning with Consistency and Confidence

2020-01-21 · NeurIPS 2020 12 · Kihyuk Sohn, David Berthelot, Chun-Liang Li, Zizhao Zhang, Nicholas Carlini, Ekin D. Cubuk, Alex Kurakin, Han Zhang, Colin Raffel

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.

📄 PDF Abstract BibTeX arXiv:2001.07685

Code (26)

google-research/fixmatch 공식 구현 tf
A-Telfer/AugKey
AhmadQasim/FixMatch pytorch
Celiali/FixMatch pytorch
CoinCheung/fixmatch pytorch
CoinCheung/fixmatch-pytorch pytorch
DonghwanKIM0101/CS492I_CV pytorch
KaiyangZhou/ssdg-benchmark pytorch
LeeDoYup/FixMatch-pytorch pytorch
OFRIN/Tensorflow_FixMatch tf
S-HuaBomb/FixMatch-Paddle paddle
SaraAmd/Semi-Supervised-Learning pytorch
Trayan7/FixMatch-with-Soft-Labels tf
Valentyn1997/semi-supervised-text-classification pytorch
Zhongying-Deng/NorMatch pytorch
amazon-research/exponential-moving-average-normalization pytorch
fbuchert/fixmatch-pytorch pytorch
gomezzz/MSMatch pytorch
gomezzz/distmsmatch pytorch
google-research/crest tf
johnchenresearch/SSL tf
kekmodel/FixMatch-pytorch pytorch
miquelmarti/DenseFixMatch pytorch
phanav/fixmatch-fastai pytorch
ptrckhmmr/learning-to-defer-with-limited-expert-predictions pytorch
valencebond/FixMatch_pytorch pytorch

Tasks

Image ClassificationPseudo LabelSemi-Supervised Image Classification

Methods 이 논문이 사용한 방법론

FixMatch 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…

Similar Papers 제목 키워드 기반

FixMatch: Simplifying Semi-Supervised Learning with Consistency and Confidence

2020-01-21 · Kihyuk Sohn∗ David Berthelot∗ Chun-Liang Li Zizhao Zhang Nicholas Carlini Ekin D. Cubuk Alex Kurakin Han Zhang Colin Raffel

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 Label

AlphaMatch: Improving Consistency for Semi-supervised Learning with Alpha-divergence

2020-11-23 · CVPR 2021 1 · Chengyue Gong, Dilin Wang, Qiang Liu

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

2020-12-06 · RC 2020 · Ci Li, Ruibo Tu, HUI ZHANG

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 Classification

Dense FixMatch: a simple semi-supervised learning method for pixel-wise prediction tasks

2022-10-18 · Miquel Martí i Rabadán, Alessandro Pieropan, Hossein Azizpour, Atsuto Maki

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 Segmentation

OpenMatch: Open-set Consistency Regularization for Semi-supervised Learning with Outliers

2021-05-28 · Kuniaki Saito, Donghyun Kim, Kate Saenko

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