Attribute-Based Classification for Zero-Shot Visual Object Categorization
Top Cited Papers
- 30 July 2013
- journal article
- research article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Pattern Analysis and Machine Intelligence
- Vol. 36 (3), 453-465
- https://doi.org/10.1109/tpami.2013.140
Abstract
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.Keywords
This publication has 47 references indexed in Scilit:
- SmcHD1, containing a structural-maintenance-of-chromosomes hinge domain, has a critical role in X inactivationNature Genetics, 2008
- Kernel Methods in Computer VisionFoundations and Trends® in Computer Graphics and Vision, 2007
- Memory modulates color appearanceNature Neuroscience, 2006
- A Decision-Theoretic Generalization of On-Line Learning and an Application to BoostingJournal of Computer and System Sciences, 1997
- Hierarchical Mixtures of Experts and the EM AlgorithmNeural Computation, 1994
- Extrapolating human probability judgmentTheory and Decision, 1994
- Feature-Based InductionCognitive Psychology, 1993
- Two Notes on NotationThe American Mathematical Monthly, 1992
- Default ProbabilityCognitive Science, 1991
- Recognition-by-components: A theory of human image understanding.Psychological Review, 1987