UM  > 科技學院  > 電腦及資訊科學系
Cross-scene learning: Improving classification performance by using "gray sample
Liu C.W.2; Shang Z.W.2; Tang Y.Y.1
2014
Conference Name2014 IEEE International Conference on Systems, Man, and Cybernetics (SMC)
Source PublicationConference Proceedings - IEEE International Conference on Systems, Man and Cybernetics
Volume2014-January
IssueJanuary
Pages4077-4084
Conference Date5-8 Oct. 2014
Conference PlaceSan Diego, CA
CountryUSA
PublisherIEEE, 345 E 47TH ST, NEW YORK, NY 10017 USA
Abstract

Most object classification models considered in image only exist positive samples and negative samples. In this paper, another type of sample exists, named "gray sample", which belongs to neither positive samples nor negative samples, contains knowledge in other domains or scenes. The degree of "gray" is defined by semantic similarity between annotations and scenes. While the local descriptors represent one object by visual feature, and the annotations are semantic description of this object. One class of objects has exclusive concept and different descriptions in different scenes, "gray samples" is belong to one concept, but exist in other scenes by different manifestation. Only the similar scenes have commonality, which is a bridge connect knowledge in different scenes. To achieve goal of crossscene learning and using "gray sample", the similar degree of scenes is needed to be conducted, by computing the co-occurrence probability of annotations. In our model, following the bagsof- features (BoF) approach, a plenty of local descriptors are extracted from the annotation areas of images, the visual words are got through clustering those descriptors, and the proposed model is built upon the visual words. Using EM algorithm, construct model under different thresholds of correlation degree, and classify objects. The thresholds are important in decision whether the "gray samples" are suitable for training data, and key factor in classification performance. The experiments of object classification based on LabelMe dataset, the proposed model exhibits superior performances compared to the other existing methods.

DOIhttps://doi.org/10.1109/SMC.2014.6974571
URLView the original
Indexed BySCI
Language英语
WOS Research AreaComputer Science
WOS SubjectComputer Science, Artificial Intelligence ; Computer Science, Cybernetics ; Computer Science, Information Systems
WOS IDWOS:000370963704036
Fulltext Access
Citation statistics
Cited Times [WOS]:1   [WOS Record]     [Related Records in WOS]
Document TypeConference paper
CollectionDEPARTMENT OF COMPUTER AND INFORMATION SCIENCE
Affiliation1.Universidade de Macau
2.Chongqing University
Recommended Citation
GB/T 7714
Liu C.W.,Shang Z.W.,Tang Y.Y.. Cross-scene learning: Improving classification performance by using "gray sample[C]:IEEE, 345 E 47TH ST, NEW YORK, NY 10017 USA,2014:4077-4084.
Related Services
Recommend this item
Bookmark
Usage statistics
Export to Endnote
Google Scholar
Similar articles in Google Scholar
[Liu C.W.]'s Articles
[Shang Z.W.]'s Articles
[Tang Y.Y.]'s Articles
Baidu academic
Similar articles in Baidu academic
[Liu C.W.]'s Articles
[Shang Z.W.]'s Articles
[Tang Y.Y.]'s Articles
Bing Scholar
Similar articles in Bing Scholar
[Liu C.W.]'s Articles
[Shang Z.W.]'s Articles
[Tang Y.Y.]'s Articles
Terms of Use
No data!
Social Bookmark/Share
All comments (0)
No comment.
 

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