MixMatch: A Holistic Approach to Semi-Supervised Learning
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.
Code (30)
Tasks
Image ClassificationSemi-Supervised Image ClassificationSimilar Papers 제목 키워드 기반
Holistic Semi-Supervised Approaches for EEG Representation Learning
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 LearningNegative sampling in semi-supervised learning
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
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 ClassificationMixMOOD: A systematic approach to class distribution mismatch in semi-supervised learning using deep dataset dissimilarity measures
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 SimilaritySelfMatch: Combining Contrastive Self-Supervision and Consistency for Semi-Supervised Learning
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