Interactively building a discriminative vocabulary of nameable attributes
Interactively building a discriminative vocabulary of nameable attributes
复制标题
DOI：
10.1109/cvpr.2011.5995451
复制
发表时间：
2011-06
期刊：
影响因子：
--
通讯作者：
Devi Parikh;K. Grauman
中科院分区：
文献类型：
--
作者：
Devi Parikh;K. Grauman
当用作对象识别的中级特征时，人类可命名的视觉属性提供许多优点，但是收集相关属性的现有技术可能是低效的（花费大量努力或专业知识）和/或不足的（描述性属性不需要是有区别的）。我们介绍了一种方法来定义一个词汇的属性，这是人类可以理解的和歧视。该系统以对象/场景标记的图像作为输入，并返回一组属性作为输出，这些属性是从区分感兴趣的类别的人类注释器中得出的。为了确保一个紧凑的词汇表和有效地利用注释者的努力，我们1）展示了如何积极地增加词汇表，使新的属性解决类间的混乱，和2）提出了一种新的“可命名性”流形，优先考虑候选属性与可命名属性相关联的可能性。我们用多个数据集演示了这种方法，并展示了它相对于缺乏命名能力模型或依赖于专家提供的属性列表的基线的明显优势。
Human-name able visual attributes offer many advantages when used as mid-level features for object recognition, but existing techniques to gather relevant attributes can be inefficient (costing substantial effort or expertise) and/or insufficient (descriptive properties need not be discriminative). We introduce an approach to define a vocabulary of attributes that is both human understandable and discriminative. The system takes object/scene-labeled images as input, and returns as output a set of attributes elicited from human annotators that distinguish the categories of interest. To ensure a compact vocabulary and efficient use of annotators' effort, we 1) show how to actively augment the vocabulary such that new attributes resolve inter-class confusions, and 2) propose a novel "nameability" manifold that prioritizes candidate attributes by their likelihood of being associated with a nameable property. We demonstrate the approach with multiple datasets, and show its clear advantages over baselines that lack a name-ability model or rely on a list of expert-provided attributes.