CVPR 2011 (2011)
June 20, 2011 to June 25, 2011
Bangpeng Yao , Comput. Sci. Dept., Stanford Univ., Stanford, CA, USA
A. Khosla , Comput. Sci. Dept., Stanford Univ., Stanford, CA, USA
Li Fei-Fei , Comput. Sci. Dept., Stanford Univ., Stanford, CA, USA
In this paper, we study the problem of fine-grained image categorization. The goal of our method is to explore fine image statistics and identify the discriminative image patches for recognition. We achieve this goal by combining two ideas, discriminative feature mining and randomization. Discriminative feature mining allows us to model the detailed information that distinguishes different classes of images, while randomization allows us to handle the huge feature space and prevents over-fitting. We propose a random forest with discriminative decision trees algorithm, where every tree node is a discriminative classifier that is trained by combining the information in this node as well as all upstream nodes. Our method is tested on both subordinate categorization and activity recognition datasets. Experimental results show that our method identifies semantically meaningful visual information and outperforms state-of-the-art algorithms on various datasets.
randomization, grained image categorization, fine image statistics, discriminative image patches, discriminative feature mining, random forest, discriminative decision trees algorithm, discriminative classifier, activity recognition datasets
A. Khosla, Bangpeng Yao and Li Fei-Fei, "Combining randomization and discrimination for fine-grained image categorization," CVPR 2011(CVPR), Providence, RI, 2011, pp. 1577-1584.