This Article 
   
 Share 
   
 Bibliographic References 
   
 Add to: 
 
Digg
Furl
Spurl
Blink
Simpy
Google
Del.icio.us
Y!MyWeb
 
 Search 
   
Attribute-Based Classification for Zero-Shot Visual Object Categorization
March 2014 (vol. 36 no. 3)
pp. 453-465
Christoph H. Lampert, IST Austria, Klosterneuburg
Hannes Nickisch, Philips Research, Hamburg
Stefan Harmeling, Max Planck Institute for Intelligent Systems, Tübingen
We study the problem of object recognition for categories for which we have no training examples, a task also called zero--data or zero-shot learning. This situation has hardly been studied in computer vision research, even though it occurs frequently; the world contains tens of thousands of different object classes, and image collections have been formed and suitably annotated for only a few of them. To tackle the problem, we introduce attribute-based classification: Objects are identified based on a high-level description that is phrased in terms of semantic attributes, such as the object's color or shape. Because the identification of each such property transcends the specific learning task at hand, the attribute classifiers can be prelearned independently, for example, from existing image data sets unrelated to the current task. Afterward, new classes can be detected based on their attribute representation, without the need for a new training phase. In this paper, we also introduce a new data set, Animals with Attributes, of over 30,000 images of 50 animal classes, annotated with 85 semantic attributes. Extensive experiments on this and two more data sets show that attribute-based classification indeed is able to categorize images without access to any training images of the target classes.
Index Terms:
Training,Semantics,Vectors,Computer vision,Marine animals,Probabilistic logic,vision and scene understanding,Object recognition
Citation:
Christoph H. Lampert, Hannes Nickisch, Stefan Harmeling, "Attribute-Based Classification for Zero-Shot Visual Object Categorization," IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 36, no. 3, pp. 453-465, March 2014, doi:10.1109/TPAMI.2013.140
Usage of this product signifies your acceptance of the Terms of Use.