On Taxonomies for Multi-class Image Categorization
On Taxonomies for Multi-class Image Categorization
复制标题
DOI：
10.1007/s11263-010-0417-8
复制
发表时间：
2012-09-01
影响因子：
19.5
通讯作者：
Kawanabe, Motoaki
中科院分区：
文献类型：
--
作者：
Binder, Alexander;Mueller, Klaus-Robert;Kawanabe, Motoaki
我们研究了一个给定的，预先确定的分类图像分类的问题。这个任务可以优雅地转化为结构化学习框架。然而，尽管结构化学习具有强大的功能，但由于其高内存要求和缓慢的训练过程，它在可扩展性方面存在限制。我们提出了一个有效的近似结构化学习方法的集成本地支持向量机（SVM），可以有效地训练与标准技术。玩具数据的第一个理论讨论和实验允许阐明为什么基于分类法的分类可以优于无分类法的方法，以及为什么适当组合的本地SVM集成可能具有很高的实际用途。Caltech256和VOC2006数据子集的进一步实证结果确实表明，我们的本地SVM公式可以有效地利用分类结构，从而优于标准的多类分类算法，同时它实现了与基于分类的结构化算法在显着减少计算时间的同等结果。
We study the problem of classifying images into a given, pre-determined taxonomy. This task can be elegantly translated into the structured learning framework. However, despite its power, structured learning has known limits in scalability due to its high memory requirements and slow training process. We propose an efficient approximation of the structured learning approach by an ensemble of local support vector machines (SVMs) that can be trained efficiently with standard techniques. A first theoretical discussion and experiments on toy-data allow to shed light onto why taxonomy-based classification can outperform taxonomy-free approaches and why an appropriately combined ensemble of local SVMs might be of high practical use. Further empirical results on subsets of Caltech256 and VOC2006 data indeed show that our local SVM formulation can effectively exploit the taxonomy structure and thus outperforms standard multi-class classification algorithms while it achieves on par results with taxonomy-based structured algorithms at a significantly decreased computing time.