The Community for Technology Leaders
2013 IEEE Conference on Computer Vision and Pattern Recognition (2013)
Portland, OR, USA USA
June 23, 2013 to June 28, 2013
ISSN: 1063-6919
pp: 771-778
Attribute-based representation has shown great promises for visual recognition due to its intuitive interpretation and cross-category generalization property. However, human efforts are usually involved in the attribute designing process, making the representation costly to obtain. In this paper, we propose a novel formulation to automatically design discriminative "category-level attributes", which can be efficiently encoded by a compact category-attribute matrix. The formulation allows us to achieve intuitive and critical design criteria (category-separability, learn ability) in a principled way. The designed attributes can be used for tasks of cross-category knowledge transfer, achieving superior performance over well-known attribute dataset Animals with Attributes (AwA) and a large-scale ILSVRC2010 dataset (1.2M images). This approach also leads to state-of-the-art performance on the zero-shot learning task on AwA.
zero-shot learning, attribute, object recognition, attribute design, discriminative attribute, automatic attribute design, cross-category knowledge transfer

J. R. Smith, R. S. Feris, L. Cao, F. X. Yu and S. Chang, "Designing Category-Level Attributes for Discriminative Visual Recognition," 2013 IEEE Conference on Computer Vision and Pattern Recognition(CVPR), Portland, OR, USA USA, 2013, pp. 771-778.
97 ms
(Ver 3.3 (11022016))