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% accuracy that outperforms the strong previous methods such as MixMatch (52.46%), UDA (70.95%), ReMixMatch (80.9%), and FixMatch (86.19%). We note that SelfMatch can close the gap between supervised learning (95.87%) and semi-supervised learning (93.19%) by using only a few labels for each class.
@article{arxiv.2101.06480,
title = {SelfMatch: Combining Contrastive Self-Supervision and Consistency for Semi-Supervised Learning},
author = {Byoungjip Kim and Jinho Choo and Yeong-Dae Kwon and Seongho Joe and Seungjai Min and Youngjune Gwon},
journal= {arXiv preprint arXiv:2101.06480},
year = {2021}
}
Comments
4 pages, NeurIPS 2020 Workshop: Self-Supervised Learning - Theory and Practice