用于伪期望最大化的半监督对比离群点移除（SCOPE）
Semi-supervised Contrastive Outlier removal for Pseudo Expectation Maximization (SCOPE)
AI总结：
本文提出 SCOPE 方法，通过在伪标签 EM 迭代中引入离群点抑制与对比剪除机制，减少混淆错误，显著提升半监督分类准确率，并在 CIFAR-10 上取得最优结果。
摘要：
半监督学习是通过结合一个小的有标签数据集和一个可能大得多的无标签数据集来训练准确预测模型的问题。已经发展出许多半监督深度学习方法，包括伪标签、一致性正则化和对比学习技术。然而，伪标签方法极易受到混淆的影响，即在早期迭代中错误的伪标签被假定为真实标签，从而导致模型强化其先验偏差，进而无法泛化到强预测性能。我们提出了一种通过我们称之为用于伪期望最大化的半监督对比离群点移除（SCOPE）的方法来抑制混淆错误的新方法。与基本伪标签类似，SCOPE 与期望最大化（EM）相关，EM 是一种潜变量框架，可以扩展用于理解聚类假设的深度半监督算法。然而，与未能充分考虑给定模型下无标签样本概率的基本伪标签不同，SCOPE 引入了一个离群点抑制项，旨在在存在离群点的情况下，给定判别 DNN 骨干网络时改善 EM 迭代的行为。我们的结果表明，SCOPE 相较于基线大幅提高了半监督分类准确率，并且在与一致性正则化结合时，在使用 250 和 4000 个有标签样本的半监督 CIFAR-10 分类任务上取得了已报告的最高准确率。此外，我们表明 SCOPE 通过剪除错误的高置信度伪标签样本（这些样本否则会在后续重训练迭代中污染有标签集），降低了伪标签迭代过程中混淆错误的发生率。
英文摘要：
Semi-supervised learning is the problem of training an accurate predictive model by combining a small labeled dataset with a presumably much larger unlabeled dataset. Many methods for semi-supervised deep learning have been developed, including pseudolabeling, consistency regularization, and contrastive learning techniques. Pseudolabeling methods however are highly susceptible to confounding, in which erroneous pseudolabels are assumed to be true labels in early iterations, thereby causing the model to reinforce its prior biases and thereby fail to generalize to strong predictive performance. We present a new approach to suppress confounding errors through a method we describe as Semi-supervised Contrastive Outlier removal for Pseudo Expectation Maximization (SCOPE). Like basic pseudolabeling, SCOPE is related to Expectation Maximization (EM), a latent variable framework which can be extended toward understanding cluster-assumption deep semi-supervised algorithms. However, unlike basic pseudolabeling which fails to adequately take into account the probability of the unlabeled samples given the model, SCOPE introduces an outlier suppression term designed to improve the behavior of EM iteration given a discrimination DNN backbone in the presence of outliers. Our results show that SCOPE greatly improves semi-supervised classification accuracy over a baseline, and furthermore when combined with consistency regularization achieves the highest reported accuracy for the semi-supervised CIFAR-10 classification task using 250 and 4000 labeled samples. Moreover, we show that SCOPE reduces the prevalence of confounding errors during pseudolabeling iterations by pruning erroneous high-confidence pseudolabeled samples that would otherwise contaminate the labeled set in subsequent retraining iterations.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
