| How to use Bag-of-Words model better for image classification |
| Wang, Chong; Huang, Kaiqi
|
发表期刊 | IMAGE AND VISION COMPUTING
|
| 2015-06-01
|
卷号 | 38期号:0页码:65-74 |
文章类型 | Article
|
摘要 | The Bag-of-Words (BoW) framework is well-known in image classification. In the framework, there are two essential steps: 1) coding, which encodes local features by a visual vocabulary, and 2) pooling, which pools over the response of all features into image representation. Many coding and pooling methods are proposed, and how to apply them better in different conditions has become a practical problem. In this paper, to better use BoW in different applications, we study the relation between many typical coding methods and two popular pooling methods. Specifically, complete combinations of coding and pooling are evaluated based on an extremely large range of vocabulary sizes (16 to 1M) on five primary and popular datasets. Three typical ones are 15 Scenes, Caltech 101 and PASCAL VOC 2007, while the other two large-scale ones are Caltech 256 and ImageNet. Based on the systematic evaluation, some interesting conclusions are drawn. Some conclusions are the extensions of previous viewpoints, while some are different but important to understand BoW model. Based on these conclusions, we provide detailed application criterions by evaluating coding and pooling based on precision, efficiency and memory requirements in different applications. We hope that this study can be helpful to evaluate different coding and pooling methods, the conclusions can be beneficial to better understand BoW, and the application criterions can be valuable to use BoW better indifferent applications. (C) 2014 Elsevier B.V. All rights reserved. |
关键词 | Image Classification
Bag-of-words
Visual Vocabulary
Coding
Pooling
|
WOS标题词 | Science & Technology
; Technology
; Physical Sciences
|
关键词[WOS] | VISUAL-CORTEX
|
收录类别 | SCI
|
语种 | 英语
|
WOS研究方向 | Computer Science
; Engineering
; Optics
|
WOS类目 | Computer Science, Artificial Intelligence
; Computer Science, Software Engineering
; Computer Science, Theory & Methods
; Engineering, Electrical & Electronic
; Optics
|
WOS记录号 | WOS:000356196400006
|
引用统计 |
|
文献类型 | 期刊论文
|
条目标识符 | http://ir.ia.ac.cn/handle/173211/7938
|
专题 | 智能感知与计算研究中心
|
作者单位 | Chinese Acad Sci, Inst Automat, Natl Lab Pattern Recognit, Beijing 100864, Peoples R China
|
第一作者单位 | 模式识别国家重点实验室
|
推荐引用方式 GB/T 7714 |
Wang, Chong,Huang, Kaiqi. How to use Bag-of-Words model better for image classification[J]. IMAGE AND VISION COMPUTING,2015,38(0):65-74.
|
APA |
Wang, Chong,&Huang, Kaiqi.(2015).How to use Bag-of-Words model better for image classification.IMAGE AND VISION COMPUTING,38(0),65-74.
|
MLA |
Wang, Chong,et al."How to use Bag-of-Words model better for image classification".IMAGE AND VISION COMPUTING 38.0(2015):65-74.
|
修改评论