首页> 外文期刊>Neural Networks and Learning Systems, IEEE Transactions on >Visual Recognition by Learning From Web Data via Weakly Supervised Domain Generalization
【24h】

Visual Recognition by Learning From Web Data via Weakly Supervised Domain Generalization

机译:通过弱监督域泛化从Web数据中学习来进行视觉识别

获取原文
获取原文并翻译 | 示例

摘要

In this paper, a weakly supervised domain generalization (WSDG) method is proposed for real-world visual recognition tasks, in which we train classifiers by using Web data (e.g., Web images and Web videos) with noisy labels. In particular, two challenging problems need to be solved when learning robust classifiers, in which the first issue is to cope with the label noise of training Web data from the source domain, while the second issue is to enhance the generalization capability of learned classifiers to an arbitrary target domain. In order to handle the first problem, the training samples within each category are partitioned into clusters, where we use one bag to denote each cluster and instances to denote the samples in each cluster. Then, we identify a proportion of good training samples in each bag and train robust classifiers by using the good training samples, which leads to a multi-instance learning (MIL) problem. In order to handle the second problem, we assume that the training samples possibly form a set of hidden domains, with each hidden domain associated with a distinctive data distribution. Then, for each category and each hidden latent domain, we propose to learn one classifier by extending our MIL formulation, which leads to our WSDG approach. In the testing stage, our approach can obtain better generalization capability by effectively integrating multiple classifiers from different latent domains in each category. Moreover, our WSDG approach is further extended to utilize additional textual descriptions associated with Web data as privileged information (PI), although testing data do not have such PI. Extensive experiments on three benchmark data sets indicate that our newly proposed methods are effective for real-world visual recognition tasks by learning from Web data.
机译:本文针对现实世界中的视觉识别任务提出了一种弱监督域综合(WSDG)方法,其中我们通过使用带有噪声标签的Web数据(例如Web图像和Web视频)来训练分类器。特别是在学习鲁棒的分类器时,需要解决两个具有挑战性的问题,其中第一个问题是应对来自源域的训练Web数据的标签噪声,而第二个问题是增强学习的分类器的泛化能力,以解决这些问题。任意目标域。为了解决第一个问题,将每个类别中的训练样本分为几类,在这里我们使用一个袋子来表示每个类,并使用实例来表示每个类中的样本。然后,我们在每个袋子中确定一部分良好的训练样本,并通过使用良好的训练样本来训练鲁棒的分类器,这将导致多实例学习(MIL)问题。为了处理第二个问题,我们假设训练样本可能形成一组隐藏域,每个隐藏域都与独特的数据分布相关联。然后,对于每个类别和每个隐藏的潜在领域,我们建议通过扩展MIL公式来学习一个分类器,从而得出WSDG方法。在测试阶段,我们的方法可以通过有效地集成每个类别中不同潜域的多个分类器来获得更好的泛化能力。而且,我们的WSDG方法得到了进一步扩展,以利用与Web数据关联的其他文本描述作为特权信息(PI),尽管测试数据没有这样的PI。在三个基准数据集上进行的大量实验表明,通过从Web数据中学习,我们新提出的方法对于现实世界中的视觉识别任务是有效的。

著录项

相似文献

  • 外文文献
  • 中文文献
  • 专利
获取原文

客服邮箱:kefu@zhangqiaokeyan.com

京公网安备:11010802029741号 ICP备案号:京ICP备15016152号-6 六维联合信息科技 (北京) 有限公司©版权所有
  • 客服微信

  • 服务号