Learning to detect unseen object classes by between-class attribute transfer
Learning to detect unseen object classes by between-class attribute transfer
复制标题
DOI：
10.1109/cvpr.2009.5206594
复制
发表时间：
2009-06
期刊：
影响因子：
--
通讯作者：
Christoph H. Lampert;H. Nickisch;S. Harmeling
中科院分区：
文献类型：
--
作者：
Christoph H. Lampert;H. Nickisch;S. Harmeling
我们研究了训练和测试类不相交时的对象分类问题，即没有目标类的训练示例。这种设置在计算机视觉研究中几乎没有被研究过，但它是规则而不是例外，因为世界包含成千上万个不同的对象类，并且只有很少的图像，集合已经形成并使用合适的类标签进行注释。在本文中，我们通过引入基于属性的分类来解决这个问题。它基于人类指定的目标对象的高级描述而不是训练图像来执行对象检测。描述由任意语义属性组成，如形状，颜色甚至地理信息。因为这些属性超越了手头的特定学习任务，所以它们可以预先学习，例如从与当前任务无关的图像数据集中学习。之后，可以基于其属性表示来检测新的类，而不需要新的训练阶段。为了评估我们的方法并促进该领域的研究，我们组装了一个新的大规模数据集“具有属性的动物”，其中包含超过30，000张动物图像，这些图像与Osherson经典表格中的50个类别相匹配，该表格显示了人类如何将85个语义属性与动物类别联系起来。我们的实验表明，通过使用属性层，它确实是可以建立一个学习对象检测系统，不需要任何训练图像的目标类。
We study the problem of object classification when training and test classes are disjoint, i.e. no training examples of the target classes are available. This setup has hardly been studied in computer vision research, but it is the rule rather than the exception, because the world contains tens of thousands of different object classes and for only a very few of them image, collections have been formed and annotated with suitable class labels. In this paper, we tackle the problem by introducing attribute-based classification. It performs object detection based on a human-specified high-level description of the target objects instead of training images. The description consists of arbitrary semantic attributes, like shape, color or even geographic information. Because such properties transcend the specific learning task at hand, they can be pre-learned, e.g. from image datasets unrelated to the current task. Afterwards, new classes can be detected based on their attribute representation, without the need for a new training phase. In order to evaluate our method and to facilitate research in this area, we have assembled a new large-scale dataset, “Animals with Attributes”, of over 30,000 animal images that match the 50 classes in Osherson's classic table of how strongly humans associate 85 semantic attributes with animal classes. Our experiments show that by using an attribute layer it is indeed possible to build a learning object detection system that does not require any training images of the target classes.