论文标题

重新审视深度半监督的学习:经验分布对齐框架及其概括框架

Revisiting Deep Semi-supervised Learning: An Empirical Distribution Alignment Framework and Its Generalization Bound

论文作者

Wang, Feiyu, Wang, Qin, Li, Wen, Xu, Dong, Van Gool, Luc

论文摘要

在这项工作中,我们从明确减少标记和未标记样本之间的经验分布不匹配的新角度重新审视了半监督的学习(SSL)问题。从这个新的角度受益,我们首先提出了一个新的深度半监督的学习框架,称为半佩斯特尔的学习通过经验分布对齐(SLEDA),其中,从域适应社区中现有的技术可以轻松地用于解决半纯粹的学习问题,以通过降低经验分配距离和无标记的数据来解决半精神错乱的学习问题。基于此框架,我们还为研究界开发了一种新的理论概括,以更好地了解半监督的学习问题,在该问题中,我们可以通过将标记数据的训练错误以及标记的标记分布距离和未标记数据之间的经验分配距离最小化,可以有效地界定半监督学习的概括。在我们的新框架和理论结合的基础上,我们通过同时采用域名适应性群落的良好成熟的对抗性培训策略,并制定了一种称为增强分配对准网络(ADA-NET)的简单有效的半监督学习方法,称为增强分配对准网络(ADA-NET),并采用了一个简单的样本插入式插入策略来增强数据的数据。此外,我们将这两种策略都纳入了两种退出的SSL方法,以进一步提高其概括能力,这表明我们的新框架为解决SSL问题提供了补充解决方案。对于半监督的图像识别任务,我们在两个基准数据集SVHN和CIFAR-10上进行了全面的实验结果,对于半监督点云识别任务,我们为SSL提供的有效性证明了SSL的有效性。

In this work, we revisit the semi-supervised learning (SSL) problem from a new perspective of explicitly reducing empirical distribution mismatch between labeled and unlabeled samples. Benefited from this new perspective, we first propose a new deep semi-supervised learning framework called Semi-supervised Learning by Empirical Distribution Alignment (SLEDA), in which existing technologies from the domain adaptation community can be readily used to address the semi-supervised learning problem through reducing the empirical distribution distance between labeled and unlabeled data. Based on this framework, we also develop a new theoretical generalization bound for the research community to better understand the semi-supervised learning problem, in which we show the generalization error of semi-supervised learning can be effectively bounded by minimizing the training error on labeled data and the empirical distribution distance between labeled and unlabeled data. Building upon our new framework and the theoretical bound, we develop a simple and effective deep semi-supervised learning method called Augmented Distribution Alignment Network (ADA-Net) by simultaneously adopting the well-established adversarial training strategy from the domain adaptation community and a simple sample interpolation strategy for data augmentation. Additionally, we incorporate both strategies in our ADA-Net into two exiting SSL methods to further improve their generalization capability, which indicates that our new framework provides a complementary solution for solving the SSL problem. Our comprehensive experimental results on two benchmark datasets SVHN and CIFAR-10 for the semi-supervised image recognition task and another two benchmark datasets ModelNet40 and ShapeNet55 for the semi-supervised point cloud recognition task demonstrate the effectiveness of our proposed framework for SSL.

扫码加入交流群

加入微信交流群

微信交流群二维码

扫码加入学术交流群,获取更多资源