Constructing dynamic category hierarchies for novel visual category discovery
| Autor: | Haojun Guan, Shengyong Chen, Jianwei Zhang, Ying Hu, Jianhua Zhang |
|---|---|
| Rok vydání: | 2012 |
| Předmět: |
Cognitive systems
business.industry Feature extraction LabelMe Pascal (programming language) Machine learning computer.software_genre Latent Dirichlet allocation Visualization symbols.namesake Image database symbols Artificial intelligence Category theory business computer computer.programming_language Mathematics |
| Zdroj: | IROS |
| Popis: | Category hierarchies are commonly used to compactly represent large numbers of categories and reduce the complexity of the classification problem. In this paper we introduce a novel and extended application of category hierarchies which is a powerful novel framework developed to construct dynamic category hierarchies and automatically discover novel visual categories. The dynamic is a characteristic of category hierarchies which can facilitate an important cognitive ability, the discovering of novel categories. We develop a constrained hierarchical latent Dirichlet allocation to build accurate category hierarchies. We employ object attributes as features to describe objects, which can transfer knowledge across categories and can efficiently describe novel categories. By combining them in the novel framework, novel visual object categories can be efficiently discovered and described. Extensive experiments based on PASCAL VOC 2008 and the LabelMe image database show the satisfactory performance of the proposed framework. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|