SelfMatch: Combining Contrastive Self-Supervision and Consistency for Semi-Supervised Learning
share
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-training based on contrastive learning and (2) semi-supervised fine-tuning based on augmentation consistency regularization. We empirically demonstrate that SelfMatch achieves the state-of-the-art results on standard benchmark datasets such as CIFAR-10 and SVHN. For example, for CIFAR-10 with 40 labeled examples, SelfMatch achieves 93.19 previous methods such as MixMatch (52.46 and FixMatch (86.19 supervised learning (95.87 only a few labels for each class.
READ FULL TEXT