Attribute annotation on large-scale image database by active knowledge transfer
Attribute annotation on large-scale image database by active knowledge transfer
复制标题
DOI：
10.1016/j.imavis.2018.06.012
复制
发表时间：
2018-10
期刊：
影响因子：
--
通讯作者：
Huajie Jiang;Ruiping Wang;Yan Li;Haomiao Liu;S. Shan;Xilin Chen
中科院分区：
文献类型：
--
作者：
Huajie Jiang;Ruiping Wang;Yan Li;Haomiao Liu;S. Shan;Xilin Chen
属性在不同的视觉任务中被广泛使用。然而，现有的属性资源是相当有限的，大多数都不是大规模的。目前的属性标注过程一般由人工完成，成本高，耗时长。在本文中，我们提出了一个新的框架来执行有效的属性注释。基于属性可以在不同类之间共享的常识，我们利用迁移学习和主动学习的优点，将知识从一些现有的小属性数据库迁移到大规模的目标数据库。为了学习更强大的属性模型，属性关系被纳入，以协助学习过程。使用所提出的框架，我们进行了广泛的实验上的两个大规模的图像数据库，即ImageNet和SUN属性，其中获得高质量的自动属性注释。
Attributes are widely used in different vision tasks. However, existing attribute resources are quite limited and most of them are not in large scale. Current attribute annotation process is generally done by human, which is expensive and time-consuming. In this paper, we propose a novel framework to perform effective attribute annotations. Based on the common knowledge that attributes can be shared among different classes, we leverage the benefits of transfer learning and active learning together to transfer knowledge from some existing small attribute databases to large-scale target databases. In order to learn more robust attribute models, attribute relationships are incorporated to assist the learning process. Using the proposed framework, we conduct extensive experiments on two large-scale image databases, i.e. ImageNet and SUN Attribute, where high quality automatic attribute annotations are obtained.