arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1401.7713cs.CV
收藏

一种通用的压缩码本生成概率框架

A Generalized Probabilistic Framework for Compact Codebook Creation

The Australian National University(澳大利亚国立大学);University of Wollongong(伍伦贡大学);The University of Adelaide(阿德莱德大学)

Lingqiao Liu, Lei Wang, Chunhua Shen

摘要:

在许多视觉识别任务中,紧凑且有区别的视觉码本是优选的。在文献中,许多作品已经采取了分层合并的初始大尺寸码本的视觉单词的方法,但实现这种方法与不同的合并标准。在这项工作中,我们提出了一个单一的概率框架来统一这些合并标准,通过确定两个关键因素:用于建模类条件分布的函数和用于估计分布参数的方法。更重要的是,通过采用新的分布函数和/或参数估计方法,我们的框架可以很容易地产生一系列新的合并标准。其中三个是专门针对这项工作。在第一个准则中,我们采用多项分布和贝叶斯方法;在第二个准则中,我们结合高斯分布和极大似然参数估计。在第三个准则中,表现出最好的合并性能,我们提出了一个最大间隔为基础的参数估计方法,并将其应用于多项分布。通过大量的实验研究,系统地分析了上述三个标准的性能,并与现有的标准进行了比较。如所示,在我们的框架中获得的最佳标准实现了整体最佳的合并性能之间的可比合并标准在文献中开发。

英文摘要:

Compact and discriminative visual codebooks are preferred in many visual recognition tasks. In the literature, a number of works have taken the approach of hierarchically merging visual words of an initial large-sized codebook, but implemented this approach with different merging criteria. In this work, we propose a single probabilistic framework to unify these merging criteria, by identifying two key factors: the function used to model class-conditional distribution and the method used to estimate the distribution parameters. More importantly, by adopting new distribution functions and/or parameter estimation methods, our framework can readily produce a spectrum of novel merging criteria. Three of them are specifically focused in this work. In the first criterion, we adopt the multinomial distribution with Bayesian method; In the second criterion, we integrate Gaussian distribution with maximum likelihood parameter estimation. In the third criterion, which shows the best merging performance, we propose a max-margin-based parameter estimation method and apply it with multinomial distribution. Extensive experimental study is conducted to systematically analyse the performance of the above three criteria and compare them with existing ones. As demonstrated, the best criterion obtained in our framework achieves the overall best merging performance among the comparable merging criteria developed in the literature.

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。

↑