Multi-level Discriminative Dictionary Learning towards Hierarchical Visual Categorization

Citations Over TimeTop 10% of 2013 papers

Abstract

For the task of visual categorization, the learning model is expected to be endowed with discriminative visual feature representation and flexibilities in processing many categories. Many existing approaches are designed based on a flat category structure, or rely on a set of pre-computed visual features, hence may not be appreciated for dealing with large numbers of categories. In this paper, we propose a novel dictionary learning method by taking advantage of hierarchical category correlation. For each internode of the hierarchical category structure, a discriminative dictionary and a set of classification models are learnt for visual categorization, and the dictionaries in different layers are learnt to exploit the discriminative visual properties of different granularity. Moreover, the dictionaries in lower levels also inherit the dictionary of ancestor nodes, so that categories in lower levels are described with multi-scale visual information using our dictionary learning approach. Experiments on Image Net object data subset and SUN397 scene dataset demonstrate that our approach achieves promising performance on data with large numbers of classes compared with some state-of-the-art methods, and is more efficient in processing large numbers of categories.

Related Papers

• → The neurobiology of categorization(2010)4 cited
• Information granularity,information entropy and decision tree(2009)
• → Temporal Granularity(1995)10 cited
• → A Study of a New Colour Granularity Formula(1981)1 cited
• Study of Approximate Periodicity Mining with Multi-granularity Time(2010)