arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1502.01823cs.LGcs.CV
收藏

多分类器系统的无监督融合权值学习

Unsupervised Fusion Weight Learning in Multiple Classifier Systems

Carnegie Mellon University(卡内基梅隆大学)

Anurag Kumar, Bhiksha Raj

摘要:

在本文中,我们提出了一种无监督的方法来学习的权重,多个分类器的分数必须结合在分类器融合设置。我们还介绍了一种新的度量排名的基础上的索引,它取决于训练点的加权分数之间的加权分数的测试点的排名的实例。我们表明,优化后的索引可以用于计算的措施,如平均精度。与大多数分类器融合方法不同的是,我们的方法学习了特定于实例的权重。该问题被公式化为学习使清晰度指数最大化的权重;随后,指数本身和学习到的权重都被分别用于对所有测试点进行排名。我们的方法给出了一种在实际测试数据上优化性能的无监督方法,不像众所周知的基于堆栈的方法,其中优化是在标记的训练集上完成的。此外,我们表明,我们的方法是宽容的噪声分类器,可用于选择N-最好的分类。

英文摘要:

In this paper we present an unsupervised method to learn the weights with which the scores of multiple classifiers must be combined in classifier fusion settings. We also introduce a novel metric for ranking instances based on an index which depends upon the rank of weighted scores of test points among the weighted scores of training points. We show that the optimized index can be used for computing measures such as average precision. Unlike most classifier fusion methods where a single weight is learned to weigh all examples our method learns instance-specific weights. The problem is formulated as learning the weight which maximizes a clarity index; subsequently the index itself and the learned weights both are used separately to rank all the test points. Our method gives an unsupervised method of optimizing performance on actual test data, unlike the well known stacking-based methods where optimization is done over a labeled training set. Moreover, we show that our method is tolerant to noisy classifiers and can be used for selecting N-best classifiers.

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。

↑