RealMix: Towards Realistic Semi-Supervised Deep Learning Algorithms

18 Dec 2019Varun NairJavier Fuentes AlonsoTony Beltramelli

Semi-Supervised Learning (SSL) algorithms have shown great potential in training regimes when access to labeled data is scarce but access to unlabeled data is plentiful. However, our experiments illustrate several shortcomings that prior SSL algorithms suffer from... (read more)

PDF Abstract
TASK DATASET MODEL METRIC NAME METRIC VALUE GLOBAL RANK RESULT LEADERBOARD
Semi-Supervised Image Classification cifar10, 250 Labels RealMix Percentage correct 90.21 # 3
Semi-Supervised Image Classification CIFAR-10, 250 Labels EnAET Accuracy 92.4 # 3
Semi-Supervised Image Classification CIFAR-10, 250 Labels RealMix Accuracy 90.21 # 4
Semi-Supervised Image Classification CIFAR-10, 4000 Labels RealMix Accuracy 93.62 # 8
Semi-Supervised Image Classification SVHN, 250 Labels RealMix Accuracy 96.47 # 2

Methods used in the Paper


METHOD TYPE
🤖 No Methods Found Help the community by adding them if they're not listed; e.g. Deep Residual Learning for Image Recognition uses ResNet