Sciweavers

Share
CVPR
2009
IEEE

Learning To Detect Unseen Object Classes by Between-Class Attribute Transfer

10 years 5 months ago
Learning To Detect Unseen Object Classes by Between-Class Attribute Transfer
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 attribut...
Christoph H. Lampert, Hannes Nickisch, Stefan Harm
Added 05 May 2009
Updated 10 Dec 2009
Type Conference
Year 2009
Where CVPR
Authors Christoph H. Lampert, Hannes Nickisch, Stefan Harmeling
Comments (0)
books