Semi-supervised learning has achieved notable success by leveraging very few labeled data and exploiting the wealth of information derived from unlabeled data. However, existing algorithms usually focus on aligning predictions on paired data points augmented from an identical source, and overlook the inter-point relationships within each batch. This paper introduces a novel method, RelationMatch, which exploits in-batch relationships with a matrix cross-entropy (MCE) loss function. Through the application of MCE, our proposed method consistently surpasses the performance of established state-of-the-art methods, such as FixMatch and FlexMatch, across a variety of vision datasets. Notably, we observed a substantial enhancement of 15.21% in accuracy over FlexMatch on the STL-10 dataset using only 40 labels. Moreover, we apply MCE to supervised learning scenarios, and observe consistent improvements as well.

翻译：半监督学习通过利用极少量标注数据并充分挖掘无标注数据中蕴含的丰富信息，已取得显著成功。然而，现有算法通常侧重于对齐从同一数据源增强得到的成对数据点的预测结果，而忽略了每个批次内数据点间的关系。本文提出了一种名为RelationMatch的新方法，该方法通过矩阵交叉熵（MCE）损失函数来利用批量内关系。通过应用MCE，我们提出的方法在多个视觉数据集上持续超越了FixMatch和FlexMatch等现有最先进方法。值得注意的是，在仅使用40个标签的STL-10数据集上，我们观察到相较于FlexMatch，准确率提升高达15.21%。此外，我们将MCE应用于监督学习场景，同样观察到一致性的性能提升。