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

21 Nov 2019David BerthelotNicholas CarliniEkin D. CubukAlex KurakinKihyuk SohnHan ZhangColin 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... (read more)

PDF Abstract
TASK DATASET MODEL METRIC NAME METRIC VALUE GLOBAL RANK RESULT LEADERBOARD
Semi-Supervised Image Classification cifar10, 250 Labels ReMixMatch Percentage correct 93.73 # 1
Semi-Supervised Image Classification CIFAR-10, 250 Labels ReMixMatch Accuracy 93.73 # 2
Semi-Supervised Image Classification CIFAR-10, 4000 Labels ReMixMatch Accuracy 94.86 # 4
Semi-Supervised Image Classification CIFAR-10, 40 Labels ReMixMatch Percentage error 19.10 # 3
Semi-Supervised Image Classification STL-10, 1000 Labels ReMixMatch Accuracy 93.82 # 2
Semi-Supervised Image Classification SVHN, 1000 labels ReMixMatch Accuracy 97.17 # 4

Methods used in the Paper