• 主题
高级搜索  >
历史搜索 清空历史
首页> 外文学位 >Learning with more data and better models for visual similarity and differentiation.
【24h】

Learning with more data and better models for visual similarity and differentiation.

机译：学习更多的数据和更好的视觉相似性和差异性模型。

获取原文
获取原文并翻译 | 示例
页面导航
  • 摘要
  • 著录项
  • 相似文献
  • 相关主题

摘要

This thesis studies machine learning problems involved in visual recognition on a variety of computer vision tasks. It attacks the challenge of scaling-up learning to efficiently handle more training data in object recognition, more noise in brain activation patterns, and learning more capable visual similarity models.;For learning similarity models, one challenge is to capture from data the subtle correlations that preserve the notion of similarity relevant to the task. Most previous work focused on improving feature learning and metric learning separately. Instead, we propose a unified deep-learning modeling framework that jointly optimizes the two through back-propagation. We model the feature mapping using a convolutional neural network and the metric function using a multi-layer fully-connected network. Enabled by large datasets and a sampler to handle the intrinsic imbalance between positive and negative samples, we are able to learn such models efficiently. We apply this approach to patch-based image matching and cross-domain clothing-item matching.;For analyzing activation patterns in images acquired using functional Magnetic Resonance Imaging (fMRI), a technology widely used in neuroscience to study human brain, challenges are small number of examples and high level of noise. The common ways of increasing the signal to noise ratio include adding more repetitions, averaging trials, and analyzing statistics maps solved based on a general linear model. In collaboration with neuroscientists, we developed a machine learning approach that allows us to analyze individual trials directly. This approach uses multi-voxel patterns over regions of interest as feature representation, and helps discover effects previous analyses missed.;For multi-class object recognition, one challenge is learning a non-one-vs-all multi-class classifier with large numbers of categories each with large numbers of examples. A common approach is data parallelization in a synchronized fashion: evenly and randomly distribute the data into splits, learn a full model on each split and average the models. We reformulate the overall learning problem in a consensus optimization framework and propose a more principled synchronized approach to distributed training. Moreover, we develop an efficient algorithm for solving the sub-problem by reducing it to a standard problem with warm start.
机译：本文研究了涉及多种计算机视觉任务的视觉识别中的机器学习问题。它挑战了扩展学习的挑战，以有效地处理更多的物体识别训练数据，更多的大脑激活模式噪声以及学习更强大的视觉相似度模型。;对于学习相似度模型而言，一项挑战是从数据中捕获微妙的相关性保留与任务相关的相似性概念。以前的大多数工作都集中于分别改进特征学习和度量学习。相反，我们提出了一个统一的深度学习建模框架，该框架通过反向传播共同优化了两者。我们使用卷积神经网络对特征映射进行建模，并使用多层完全连接网络对度量函数进行建模。通过大型数据集和采样器来处理正负样本之间的内在失衡，我们能够有效地学习此类模型。我们将这种方法应用于基于补丁的图像匹配和跨域服装项目匹配。;为了分析使用功能磁共振成像（fMRI）获得的图像中的激活模式，该功能是神经科学广泛用于研究人类大脑的技术，挑战很小例子很多，噪音很大。增加信噪比的常见方法包括添加更多重复，对试验求平均，以及分析基于通用线性模型求解的统计图。与神经科学家合作，我们开发了一种机器学习方法，可让我们直接分析各个试验。该方法使用感兴趣区域上的多体素模式作为特征表示，并帮助发现先前分析遗漏的效果。对于多类对象识别，一个挑战是学习具有大量数字的非一对多的多类分类器类别，每个类别都有大量示例。一种常见的方法是以同步方式进行数据并行化：将数据均匀且随机地分配到拆分中，在每个拆分中学习完整模型，然后对模型取平均值。我们在共识优化框架中重新制定了整体学习问题，并提出了一种更原则化的同步方式来进行分布式培训。此外，我们开发了一种有效的算法，通过将子问题简化为带有热启动的标准问题，从而解决了该子问题。

著录项

  • 作者

    Han, Xufeng.;

  • 作者单位

    The University of North Carolina at Chapel Hill.;

  • 授予单位 The University of North Carolina at Chapel Hill.;
  • 学科 Computer science.
  • 学位 Ph.D.
  • 年度 2016
  • 页码 92 p.
  • 总页数 92
  • 原文格式 PDF
  • 正文语种 eng
  • 中图分类
  • 关键词

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