paper-with-me

Papers

MixMatch: A Holistic Approach to Semi-Supervised Learning

2019-05-06 · NeurIPS 2019 12 · David Berthelot, Nicholas Carlini, Ian Goodfellow, Nicolas Papernot, Avital Oliver, Colin Raffel

Semi-supervised learning has proven to be a powerful paradigm for leveraging unlabeled data to mitigate the reliance on large labeled datasets. In this work, we unify the current dominant approaches for semi-supervised learning to produce a new algorithm, MixMatch, that works by guessing low-entropy labels for data-augmented unlabeled examples and mixing labeled and unlabeled data using MixUp. We show that MixMatch obtains state-of-the-art results by a large margin across many datasets and labeled data amounts. For example, on CIFAR-10 with 250 labels, we reduce error rate by a factor of 4 (from 38% to 11%) and by a factor of 2 on STL-10. We also demonstrate how MixMatch can help achieve a dramatically better accuracy-privacy trade-off for differential privacy. Finally, we perform an ablation study to tease apart which components of MixMatch are most important for its success.

📄 PDF Abstract BibTeX arXiv:1905.02249

Code (30)

google-research/mixmatch 공식 구현 tf
DamianValle/ScarceClassifier pytorch
DonghwanKIM0101/CS492I_CV pytorch
FelixAbrahamsson/mixmatch-pytorch pytorch
Jeffkang-94/Mixmatch-pytorch-SSL pytorch
Jeffkang-94/pytorch-MixMatch pytorch
Shubhammawa/MixMatch-Semi-Supervised-Learning pytorch
TianheWu/LGPNet pytorch
YU1ut/MixMatch-pytorch pytorch
atinghosh/mixmatch_pytorch pytorch
dLutscher/MixMatch-TransferLearning pytorch
dhx000/DGM_project tf
fbuchert/mixmatch-pytorch pytorch
filaPro/visda2019 tf
gan3sh500/mixmatch-pytorch pytorch
google-research/crest tf
kevinghst/mixmatch pytorch
ktran1/Manifold-attack pytorch
ms903-github/MixMatch-imdb pytorch
narendoraiswamy/MixMatch-pytorch-demo pytorch
noachr/MixMatch-fastai pytorch
ntozer/mixmatch-tensorflow2.0 tf
perrying/realistic-ssl-evaluation-pytorch pytorch
rit-git/Snippext_public pytorch
smkim7-kr/albu-MixMatch-pytorch pytorch
tinluu/Self-supervised-CV pytorch
uizard-technologies/realmix tf
viig99/mixmatch-freesound pytorch
yuxi120407/mixmatch_tensorflow tf
yuxi120407/semi-supervised_tensorflow2.0 tf

Tasks

Image ClassificationSemi-Supervised Image Classification

Similar Papers 제목 키워드 기반

Holistic Semi-Supervised Approaches for EEG Representation Learning

2021-09-24 · Guangyi Zhang, Ali Etemad

Recently, supervised methods, which often require substantial amounts of class labels, have achieved promising results for EEG representation learning. However, labeling EEG data is a challenging task. More recently, hol…

EEGElectroencephalogram (EEG)Emotion RecognitionRepresentation Learning

Negative sampling in semi-supervised learning

2019-11-12 · ICML 2020 1 · John Chen, Vatsal Shah, Anastasios Kyrillidis

We introduce Negative Sampling in Semi-Supervised Learning (NS3L), a simple, fast, easy to tune algorithm for semi-supervised learning (SSL). NS3L is motivated by the success of negative sampling/contrastive estimation. …

ReMixMatch: Semi-Supervised Learning with Distribution Alignment and Augmentation Anchoring

2019-11-21 · David Berthelot, Nicholas Carlini, Ekin D. Cubuk, Alex Kurakin 외

We improve the recently-proposed "MixMatch" semi-supervised learning algorithm by introducing two new techniques: distribution alignment and augmentation anchoring. Distribution alignment encourages the marginal distribu…

Image ClassificationSemi-Supervised Image Classification

MixMOOD: A systematic approach to class distribution mismatch in semi-supervised learning using deep dataset dissimilarity measures

2020-06-14 · Saul Calderon-Ramirez, Luis Oala, Jordina Torrents-Barrena, Shengxiang Yang 외

In this work, we propose MixMOOD - a systematic approach to mitigate effect of class distribution mismatch in semi-supervised deep learning (SSDL) with MixMatch. This work is divided into two components: (i) an extensive…

Multi-class ClassificationSemantic SimilaritySemantic Textual Similarity

SelfMatch: Combining Contrastive Self-Supervision and Consistency for Semi-Supervised Learning

2021-01-16 · Byoungjip Kim, Jinho Choo, Yeong-Dae Kwon, Seongho Joe 외

This paper introduces SelfMatch, a semi-supervised learning method that combines the power of contrastive self-supervised learning and consistency regularization. SelfMatch consists of two stages: (1) self-supervised pre…

Contrastive LearningSelf-Supervised LearningSemi-Supervised Image Classification