Image Classification: An Integration of Randomization and Discrimination
in A Dense Feature Representation

Bangpeng Yao       Aditya Khosla       Kyunghee Kim       Li Fei-Fei

Introduction
The goal of our method is to identify the discriminative fine-grained image region that distinguishes different classes. To achieve this goal we sample image regions from dense sampling space and use a random forest algorithm with discriminative classifier. Each node of the tree of random forest is trained and tested with fine-grained image patches combining the information from upstream nodes together. We implemented each node of the tree with a discriminative SVM classifier, which makes the node as a strong classifier.

PASCAL VOC Winner Prize
Our method achieves the best performance in 6 out of the 10 classes in the PASCAL VOC action classification challenge. The table below shows the average precision of our method for each action category.

jumping phoning playing reading riding riding running taking using walking
instrument bike horse photo computer
CAENLEAR_DSAL
62.1
39.7
60.5
33.6
80.8
83.6
80.3
23.2
53.4
50.2
CAENLEAR_HOBJ_DSAL
71.6
50.7
77.5
37.8
86.5
89.5
83.8
25.1
58.9
59.2
MISSOURI_SSLMF
58.8
36.8
48.5
30.6
81.5
83.0
78.5
21.3
50.7
53.8
NUDT_CONTEXT
65.9
41.5
57.4
34.7
88.8
90.2
87.9
25.7
54.5
59.5
NUDT_LL_SEMANTIC
66.3
41.3
53.9
35.2
88.8
90.0
87.6
25.5
53.7
58.2
WVU_SVM-PHOW
42.5
29.5
32.1
26.7
48.5
46.3
59.2
13.5
24.3
35.6
Our Method
66.0
41.0
60.0
41.5
90.0
92.1
86.6
28.8
62.0
65.9

Source Code
You can download the code of the project here. For instruction how to use the code, please open README file after extracting the files.

References
B. Yao, A. Khosla, and L. Fei-Fei. "Combining Randomization and Discrimination for Fine-Grained Image Categorization." IEEE Conference on Computer Vision and Pattern Recognition (CVPR). Colorado Springs, CO, USA. June 21-25, 2011. [PDF] [Slides] [BibTeX]

Contact
Please contact bangpeng@cs.stanford.edu if you have any question.