Beyond visual features: A weak semantic image representation using exemplar classifiers for classification
Beyond visual features: A weak semantic image representation using exemplar classifiers for classification
复制标题
DOI：
10.1016/j.neucom.2012.07.056
复制
发表时间：
2013-11
期刊：
影响因子：
6
通讯作者：
Chunjie Zhang;J. Liu;Q. Tian;Chao Liang;Qingming Huang
中科院分区：
文献类型：
--
作者：
Chunjie Zhang;J. Liu;Q. Tian;Chao Liang;Qingming Huang
通常，由于众所周知的语义差距，图像的低级表示不能满足图像分类的要求，并进一步阻碍了其在高级视觉应用中的应用。为了解决这些问题，在本文中，我们提出了一种简单但有效的图像分类图像表示，其表示为对一组示例图像分类器的响应。训练图像对应的每个样本分类器是使用SVM算法学习的，以将图像与不同类别的其他图像区分开来，从而表现出一些判别性信息，这也可以被视为一种弱语义。通过这种一对一的方式，我们可以获得所有训练图像的样本分类器。然后，我们利用弱语义图像表示的优势，为每个图像类别训练一个具有结构化稀疏约束的线性分类器。在多个公共数据集上的实验证明了所提出方法的有效性。
Usually, the low-level representation of images is unsatisfied for image classification due to the well-known semantic gap, and further hinders its application for high-level visual applications. To deal with these problems, in this paper, we propose a simple but effective image representation for image classification, which is denoted as the responses to a set of exemplar image classifiers. Each exemplar classifier corresponding to a training image is learned using SVM algorithm to distinguish the image from others in different classes, and hence exhibits some discriminative information, which can also be regarded as a kind of weak semantic meaning. In such a one-vs-all manner, we can obtain the exemplar classifiers for all training images. We then train a linear classifier with structured sparsity constraints for each image category by taking advantages of the weak semantic image representation. Experiments on several public datasets demonstrate the effectiveness of the proposed method.