• 主题
高级搜索  >
历史搜索 清空历史
首页> 外文期刊>Pattern Analysis and Machine Intelligence, IEEE Transactions on >Context-Dependent Kernels for Object Classification
【24h】

Context-Dependent Kernels for Object Classification

机译：对象分类的上下文相关内核

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

Kernels are functions designed in order to capture resemblance between data and they are used in a wide range of machine learning techniques, including support vector machines (SVMs). In their standard version, commonly used kernels such as the Gaussian one show reasonably good performance in many classification and recognition tasks in computer vision, bioinformatics, and text processing. In the particular task of object recognition, the main deficiency of standard kernels such as the convolution one resides in the lack in capturing the right geometric structure of objects while also being invariant. We focus in this paper on object recognition using a new type of kernel referred to as "context dependent.ȁD; Objects, seen as constellations of interest points, are matched by minimizing an energy function mixing 1) a fidelity term which measures the quality of feature matching, 2) a neighborhood criterion which captures the object geometry, and 3) a regularization term. We will show that the fixed point of this energy is a context-dependent kernel which is also positive definite. Experiments conducted on object recognition show that when plugging our kernel into SVMs, we clearly outperform SVMs with context-free kernels.
机译：内核是为了捕获数据之间的相似性而设计的功能，它们被广泛用于包括支持向量机（SVM）在内的机器学习技术中。在其标准版本中，常用的内核（例如高斯内核）在计算机视觉，生物信息学和文本处理的许多分类和识别任务中显示出相当好的性能。在对象识别的特定任务中，标准核（例如卷积核）的主要缺陷在于缺乏捕获对象正确的几何结构而又不变的缺点。我们在本文中将重点放在使用一种称为“上下文相关.dD”的新型内核的对象识别上；通过最小化能量函数混合来匹配被视为兴趣点星座的对象1）保真度项，该保真度项可测量特征匹配； 2）捕获对象几何形状的邻域准则； 3）正则化项；我们将证明该能量的固定点是上下文相关的核，也是正定的；对对象识别进行的实验表明：在将内核插入SVM时，使用无上下文内核的性能明显优于SVM。

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