Objects as Attributes for Scene Classification
Objects as Attributes for Scene Classification
复制标题
DOI：
10.1007/978-3-642-35749-7_5
复制
发表时间：
2010-09
期刊：
影响因子：
--
通讯作者：
Li-Jia Li-Li-Jia-Li-2040091191;Hao Su;Yongwhan Lim;Li Fei-Fei-Li-Fei-Fei-48004138
中科院分区：
文献类型：
--
作者：
Li-Jia Li-Li-Jia-Li-2040091191;Hao Su;Yongwhan Lim;Li Fei-Fei-Li-Fei-Fei-48004138
鲁棒的低级图像特征已被证明是各种高级视觉识别任务的有效表示，例如对象识别和场景分类。但随着视觉识别任务变得更具挑战性，低级特征表示和场景含义之间的语义差距越来越大。在本文中，我们建议使用对象作为场景的属性进行场景分类。我们通过收集图像对大量对象检测器或“对象过滤器”的响应来表示图像。这种表示携带高级语义信息而不是低级图像特征信息，使其更适合高级视觉识别任务。使用非常简单的现成分类器（例如 SVM），我们表明这种对象级图像表示可以有效地用于高级视觉任务（例如场景分类）。我们的结果优于在许多标准数据集上报告的最先进的性能。
Robust low-level image features have proven to be effective representations for a variety of high-level visual recognition tasks, such as object recognition and scene classification. But as the visual recognition tasks become more challenging, the semantic gap between low-level feature representation and the meaning of the scenes increases. In this paper, we propose to use objects as attributes of scenes for scene classification. We represent images by collecting their responses to a large number of object detectors, or “object filters”. Such representation carries high-level semantic information rather than low-level image feature information, making it more suitable for high-level visual recognition tasks. Using very simple, off-the-shelf classifiers such as SVM, we show that this object-level image representation can be used effectively for high-level visual tasks such as scene classification. Our results are superior to reported state-of-the-art performance on a number of standard datasets.