Learning from Error: A two-level combined model for image classification | |
Jiang, Mingyang ; Li, Chunxiao ; Deng, Zirui ; Feng, Jufu ; Wang, Liwei | |
2011 | |
英文摘要 | We propose an error learning model for image classification. Motivated by the observation that classifiers trained using local grid regions of the images are often biased, i.e., contain many classification error, we present a two-level combined model to learn useful classification information from these errors, based on Bayes rule. We give theoretical analysis and explanation to show that this error learning model is effective to correct the classification errors made by the local region classifiers. We conduct extensive experiments on benchmark image classification datasets, promising results are obtained.; http://gateway.webofknowledge.com/gateway/Gateway.cgi?GWVersion=2&SrcApp=PARTNER_APP&SrcAuth=LinksAMR&KeyUT=WOS:000313291600137&DestLinkType=FullRecord&DestApp=ALL_WOS&UsrCustomerID=8e1609b174ce4e31116a60747a720701 ; Computer Science, Artificial Intelligence; Computer Science, Hardware & Architecture; EI; CPCI-S(ISTP); 0 |
语种 | 英语 |
DOI标识 | 10.1109/ACPR.2011.6166669 |
内容类型 | 其他 |
源URL | [http://ir.pku.edu.cn/handle/20.500.11897/293130] |
专题 | 信息科学技术学院 |
推荐引用方式 GB/T 7714 | Jiang, Mingyang,Li, Chunxiao,Deng, Zirui,et al. Learning from Error: A two-level combined model for image classification. 2011-01-01. |
个性服务 |
查看访问统计 |
相关权益政策 |
暂无数据 |
收藏/分享 |
除非特别说明,本系统中所有内容都受版权保护,并保留所有权利。
修改评论