arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1909.01804cs.LGcs.CVstat.ML
收藏

Dual Student:打破教师在半监督学习中的局限

Dual Student: Breaking the Limits of the Teacher in Semi-supervised Learning

City University of Hong Kong(香港城市大学);SenseTime Research(商汤科技研究院)

Zhanghan Ke, Daoye Wang, Qiong Yan, Jimmy Ren, Rynson W. H. Lau

摘要:

最近,基于一致性的方法在半监督学习(SSL)中取得了最新的成果。这些方法总是涉及两个角色,显式或隐式教师模型和学生模型,并通过一致性约束惩罚不同扰动下的预测。然而,这两个角色的权重是紧密耦合的,因为教师本质上是学生的指数移动平均值(EMA)。在这项工作中,我们表明,耦合EMA教师造成的性能瓶颈。为了解决这个问题,我们引入了双学生,用另一个学生代替老师。我们还定义了一个新的概念,稳定的样本,以下的稳定约束设计为我们的结构是可训练的。此外,我们还讨论了我们的方法的两个变体,它们可以产生更高的性能。大量的实验表明,我们的方法提高了分类性能显着几个主要的SSL基准。具体来说,它将13层CNN的出错率在具有1 k标签的CIFAR-10上从16.84%降至12.39%,在具有10 k标签的CIFAR-100上从34.10%降至31.56%。此外,我们的方法在领域自适应方面也有明显的改进。

英文摘要:

Recently, consistency-based methods have achieved state-of-the-art results in semi-supervised learning (SSL). These methods always involve two roles, an explicit or implicit teacher model and a student model, and penalize predictions under different perturbations by a consistency constraint. However, the weights of these two roles are tightly coupled since the teacher is essentially an exponential moving average (EMA) of the student. In this work, we show that the coupled EMA teacher causes a performance bottleneck. To address this problem, we introduce Dual Student, which replaces the teacher with another student. We also define a novel concept, stable sample, following which a stabilization constraint is designed for our structure to be trainable. Further, we discuss two variants of our method, which produce even higher performance. Extensive experiments show that our method improves the classification performance significantly on several main SSL benchmarks. Specifically, it reduces the error rate of the 13-layer CNN from 16.84% to 12.39% on CIFAR-10 with 1k labels and from 34.10% to 31.56% on CIFAR-100 with 10k labels. In addition, our method also achieves a clear improvement in domain adaptation.

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。

↑