The SUN Attribute Database: Beyond Categories for Deeper Scene Understanding
The SUN Attribute Database: Beyond Categories for Deeper Scene Understanding
复制标题
DOI：
10.1007/s11263-013-0695-z
复制
发表时间：
2014-05
影响因子：
19.5
通讯作者：
Genevieve Patterson;Chen Xu;Hang Su;James Hays
中科院分区：
文献类型：
--
作者：
Genevieve Patterson;Chen Xu;Hang Su;James Hays
本文提出了第一个大规模场景属性数据库。首先，我们进行了众包的人类研究，以找到102个判别属性的分类。我们发现与材料、表面特性、照明、可视性和空间布局相关的属性。接下来，我们在多样化的SUN分类数据库的基础上构建“SUN属性数据库”。我们使用众包来标注707个场景类别中的14340张图像的属性。我们进行了大量的实验来研究场景属性和场景类别之间的相互作用。我们训练和评估属性分类器，然后研究属性作为场景分类、零拍摄学习、自动图像字幕、语义图像搜索和自然图像解析的中间场景表示的可行性。我们表明，当用作这些任务的特征时，低维场景属性可以与最先进的性能相竞争或改进。实验表明，场景属性是一种有效的低维特征，可用于捕获场景中的高级上下文和语义。
In this paper we present the first large-scale scene attribute database. First, we perform crowdsourced human studies to find a taxonomy of 102 discriminative attributes. We discover attributes related to materials, surface properties, lighting, affordances, and spatial layout. Next, we build the “SUN attribute database” on top of the diverse SUN categorical database. We use crowdsourcing to annotate attributes for 14,340 images from 707 scene categories. We perform numerous experiments to study the interplay between scene attributes and scene categories. We train and evaluate attribute classifiers and then study the feasibility of attributes as an intermediate scene representation for scene classification, zero shot learning, automatic image captioning, semantic image search, and parsing natural images. We show that when used as features for these tasks, low dimensional scene attributes can compete with or improve on the state of the art performance. The experiments suggest that scene attributes are an effective low-dimensional feature for capturing high-level context and semantics in scenes.