arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1709.05072cs.CV
收藏

联合层次类别结构学习与大规模图像分类

Joint Hierarchical Category Structure Learning and Large-Scale Image Classification

Xiamen University(厦门大学);University of Electric Science and technology of China(电子科技大学);Nara Institute of Science and Technology(奈良先端科学技术大学院大学);Institute of Automation, Chinese Academy of Sciences(中国科学院自动化研究所);University of Technology Sydney(悉尼科技大学)

Yanyun Qu, Li Lin, Fumin Shen, Chang Lu, Yang Wu, Yuan Xie, Dacheng Tao

摘要:

我们研究了具有大量类别的可扩展图像分类问题。层次化的可视化数据结构有助于提高大规模多类分类的效率和性能。提出了一种新的基于学习层次类间结构的图像分类方法。具体来说,我们首先设计了一个快速算法来计算类别之间的相似性度量,在此基础上,一个视觉树的层次谱聚类构造。使用学习的视觉树,通过在整个树上搜索最佳路径来有效地预测测试样本标签。该方法在ILSVRC 2010和Caltech 256基准数据集上进行了广泛的评估。实验结果表明,我们的方法获得了显着更好的类别层次比其他国家的最先进的视觉树为基础的方法,因此,更准确的分类。

英文摘要:

We investigate the scalable image classification problem with a large number of categories. Hierarchical visual data structures are helpful for improving the efficiency and performance of large-scale multi-class classification. We propose a novel image classification method based on learning hierarchical inter-class structures. Specifically, we first design a fast algorithm to compute the similarity metric between categories, based on which a visual tree is constructed by hierarchical spectral clustering. Using the learned visual tree, a test sample label is efficiently predicted by searching for the best path over the entire tree. The proposed method is extensively evaluated on the ILSVRC2010 and Caltech 256 benchmark datasets. Experimental results show that our method obtains significantly better category hierarchies than other state-of-the-art visual tree-based methods and, therefore, much more accurate classification.

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。

↑