CASIA OpenIR  > 模式识别国家重点实验室  > 图像与视频分析
Fast feature selection and training for AdaBoost-based concept detection with large scale datasets
Chen, Shi; Wang, Jinqiao; Liu, Yang; Xu, Changsheng; Lu, Hanqing
2010
Conference NameMM'10 - the ACM Multimedia 2010 International Conference
Source PublicationACM Multimedia Conferenc (MM)
Pages1179-1182
Conference Date2010
Conference PlaceNew York, NY, USA
AbstractAdaBoost has been proved a successful statistical learning method
for concept detection with high performance of discrimination and
generalization. However, it is computationally expensive to train a
concept detector using boosting, especially on large scale datasets.
The bottleneck of training phase is to select the best learner
among massive learners. Traditional approaches for selecting a
weak classifier usually run in 􀜱􁈺􀜰􀜶􁈻, with N examples and T
learners. In this paper, we treat the best learner selection as a
Nearest Neighbor Search problem in the function space instead of
feature space. With the help of Locality Sensitive Hashing (LSH)
algorithm, the best learner searching procedure can be speeded up
in the time of 􀜱􁈺􀜰􀜮􁈻, where L is the number of buckets in LSH.
Compared with the T (~500,000), the L (~600) is much smaller in
our experiments. In addition, through studying the distribution of
weak learners and candidate query points, we present an efficient
method to try to partition the weak learner points and the feasible
region of query points uniformly as much as possible, which can
achieve significant improvement in both recall and precision
compared with the random projection in traditional LSH
algorithm. Experimental results reveal our method can
significantly reduce the training time. And still the performance of
our method is comparable with the state-of-art methods.
KeywordFast Feature Selection And Training Adaboost-based Concept Detection
Indexed ByEI
Document Type会议论文
Identifierhttp://ir.ia.ac.cn/handle/173211/4583
Collection模式识别国家重点实验室_图像与视频分析
Corresponding AuthorWang, Jinqiao
Recommended Citation
GB/T 7714
Chen, Shi,Wang, Jinqiao,Liu, Yang,et al. Fast feature selection and training for AdaBoost-based concept detection with large scale datasets[C],2010:1179-1182.
Files in This Item: Download All
File Name/Size DocType Version Access License
Fast feature selecti(439KB)会议论文 开放获取CC BY-NC-SAView Download
Related Services
Recommend this item
Bookmark
Usage statistics
Export to Endnote
Google Scholar
Similar articles in Google Scholar
[Chen, Shi]'s Articles
[Wang, Jinqiao]'s Articles
[Liu, Yang]'s Articles
Baidu academic
Similar articles in Baidu academic
[Chen, Shi]'s Articles
[Wang, Jinqiao]'s Articles
[Liu, Yang]'s Articles
Bing Scholar
Similar articles in Bing Scholar
[Chen, Shi]'s Articles
[Wang, Jinqiao]'s Articles
[Liu, Yang]'s Articles
Terms of Use
No data!
Social Bookmark/Share
File name: Fast feature selection and training for AdaBoost-based concept detection with large scale datasets.pdf
Format: Adobe PDF
All comments (0)
No comment.
 

Items in the repository are protected by copyright, with all rights reserved, unless otherwise indicated.