论文标题
COMATT：与对比图正则化的半监督学习
CoMatch: Semi-supervised Learning with Contrastive Graph Regularization
论文作者
论文摘要
半监督学习是利用未标记数据来减少对标记数据的依赖的有效范式。我们提出了一种新的半监督学习方法COMATT，该方法统一了主要的方法并解决了它们的局限性。 COMATT共同学习培训数据的两种表示，其类别概率和低维嵌入。两种表示相互互动以共同发展。嵌入式对类别概率的平滑度约束以改善伪标记，而伪标签则通过基于图的对比度学习使嵌入式结构的结构正常化。 COMATCH在多个数据集上实现了最先进的性能。它可以在标签 - 筛分CIFAR-10和STL-10上提高准确的准确性。在带有1％标签的ImageNet上，COMATH的前1位准确性为66.0％，超过FixMatch的前1个精度率高12.6％。此外，COMATT在下游任务上可以更好地表示学习绩效，表现优于监督学习和自我监督的学习。代码和预训练模型可在https://github.com/salesforce/comatch上找到。
Semi-supervised learning has been an effective paradigm for leveraging unlabeled data to reduce the reliance on labeled data. We propose CoMatch, a new semi-supervised learning method that unifies dominant approaches and addresses their limitations. CoMatch jointly learns two representations of the training data, their class probabilities and low-dimensional embeddings. The two representations interact with each other to jointly evolve. The embeddings impose a smoothness constraint on the class probabilities to improve the pseudo-labels, whereas the pseudo-labels regularize the structure of the embeddings through graph-based contrastive learning. CoMatch achieves state-of-the-art performance on multiple datasets. It achieves substantial accuracy improvements on the label-scarce CIFAR-10 and STL-10. On ImageNet with 1% labels, CoMatch achieves a top-1 accuracy of 66.0%, outperforming FixMatch by 12.6%. Furthermore, CoMatch achieves better representation learning performance on downstream tasks, outperforming both supervised learning and self-supervised learning. Code and pre-trained models are available at https://github.com/salesforce/CoMatch.
