… a semi-supervised loss, SuNCEt, based on noise-contrastive … semi-supervised learning
accuracy of previous contrastive approaches while using less than half the amount of pre-training …

… By combining these findings, we are able to considerably outperform previous methods for
self-supervised and semi-supervised learning on ImageNet. A linear classifier trained on self-…

… As a first step in this direction, we study contrastive selfsupervised learning on four diverse
large-scale datasets. By looking through the lenses of data quantity, data domain, data quality…

… during training by the well-clustered features. On benchmarks of semi-supervised learning
tasks, our contrastive … A simple framework for contrastive learning of visual representations. In …

… We propose CoMatch, a new semi-supervised learning … CoMatch jointly learns two
representations of the training data… framework for contrastive learning of visual representations. …

… of our paper and CCLP is a promising direction for semi-supervised learning research. …
Momentum contrast for unsupervised visual representation learning. arXiv preprint arXiv:…

… visual representation learning. However, there are a lot of supervised and semi-supervised …
To fully utilize the label annotations, we propose Unified Momentum Contrast (UniMoCo), …

… a joint self-supervised contrastive visual representation learning for videos and images…
semi-supervised learning. In Proceedings of the IEEE international conference on computer vision…

… contrastive learning method SimCLR [7] and in section 4.2 we introduce attempts to improve
contrastive … In the supervised learning field and semi-supervised learning field, several …

… 44] or semi-supervised learning [6]. Recent self-supervised methods [4… is to study and
improve contrastive self-supervised methods for learning visual representations. Self-supervised …