paper-with-me

Papers

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

2019-11-21 · David Berthelot, Nicholas Carlini, Ekin D. Cubuk, Alex Kurakin, Kihyuk Sohn, Han Zhang, Colin Raffel

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 distribution of predictions on unlabeled data to be close to the marginal distribution of ground-truth labels. Augmentation anchoring feeds multiple strongly augmented versions of an input into the model and encourages each output to be close to the prediction for a weakly-augmented version of the same input. To produce strong augmentations, we propose a variant of AutoAugment which learns the augmentation policy while the model is being trained. Our new algorithm, dubbed ReMixMatch, is significantly more data-efficient than prior work, requiring between $5\times$ and $16\times$ less data to reach the same accuracy. For example, on CIFAR-10 with 250 labeled examples we reach $93.73\%$ accuracy (compared to MixMatch's accuracy of $93.58\%$ with $4{,}000$ examples) and a median accuracy of $84.92\%$ with just four labels per class. We make our code and data open-source at https://github.com/google-research/remixmatch.

📄 PDF Abstract BibTeX arXiv:1911.09785

Code (3)

google-research/mixmatch 공식 구현 tf
google-research/remixmatch 공식 구현 tf
zysymu/AdaMatch-pytorch pytorch

Tasks

Image ClassificationSemi-Supervised Image Classification

Methods 이 논문이 사용한 방법론

Sigmoid Activation 설명 없음
Tanh Activation 설명 없음
LSTM An LSTM is a type of recurrent neural network that addresses the vanishing gradient problem in vanilla…
AutoAugment 설명 없음

Similar Papers 제목 키워드 기반

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

2020-05-01 · ICLR 2020 1 · 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 distri…

SequenceMatch: Revisiting the design of weak-strong augmentations for Semi-supervised learning

2023-10-24 · Khanh-Binh Nguyen

Semi-supervised learning (SSL) has become popular in recent years because it allows the training of a model using a large amount of unlabeled data. However, one issue that many SSL methods face is the confirmation bias, …

Semi-Supervised Image ClassificationSemi-Supervised Image Classification on ImageNet - 10% labeled data

Exploring the Boundaries of Semi-Supervised Facial Expression Recognition using In-Distribution, Out-of-Distribution, and Unconstrained Data

2023-06-02 · Shuvendu Roy, Ali Etemad

Deep learning-based methods have been the key driving force behind much of the recent success of facial expression recognition (FER) systems. However, the need for large amounts of labelled data remains a challenge. Semi…

Facial Expression RecognitionFacial Expression Recognition (FER)Pseudo Label

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

SemiGPC: Distribution-Aware Label Refinement for Imbalanced Semi-Supervised Learning Using Gaussian Processes

2023-11-03 · Abdelhak Lemkhenter, Manchen Wang, Luca Zancato, Gurumurthy Swaminathan 외

In this paper we introduce SemiGPC, a distribution-aware label refinement strategy based on Gaussian Processes where the predictions of the model are derived from the labels posterior distribution. Differently from other…

Gaussian Processes