Soft pseudo-labels combined with mixup and a guaranteed labeled-sample mini-batch count outperform consistency-regularization SSL methods on CIFAR-10/100, SVHN, and Mini-ImageNet.
Focal Loss for Dense Object Detection,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2019 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Pseudo-Labeling and Confirmation Bias in Deep Semi-Supervised Learning
Soft pseudo-labels combined with mixup and a guaranteed labeled-sample mini-batch count outperform consistency-regularization SSL methods on CIFAR-10/100, SVHN, and Mini-ImageNet.