Zobrazit v EDS

Category-Independent Object Proposals with Diverse Ranking.

Uloženo v:
Podrobná bibliografie
Název: Category-Independent Object Proposals with Diverse Ranking.
Autoři: Endres, Ian, Hoiem, Derek
Zdroj: IEEE Transactions on Pattern Analysis & Machine Intelligence; Feb2014, Vol. 36 Issue 2, p222-234, 13p
Témata: OBJECT recognition (Computer vision), IMAGE segmentation, PASCAL (Computer program language), RELEVANCE ranking (Information science), DATA structures
Abstrakt: We propose a category-independent method to produce a bag of regions and rank them, such that top-ranked regions are likely to be good segmentations of different objects. Our key objectives are completeness and diversity: Every object should have at least one good proposed region, and a diverse set should be top-ranked. Our approach is to generate a set of segmentations by performing graph cuts based on a seed region and a learned affinity function. Then, the regions are ranked using structured learning based on various cues. Our experiments on the Berkeley Segmentation Data Set and Pascal VOC 2011 demonstrate our ability to find most objects within a small bag of proposed regions. [ABSTRACT FROM PUBLISHER]
Copyright of IEEE Transactions on Pattern Analysis & Machine Intelligence is the property of IEEE and its content may not be copied or emailed to multiple sites without the copyright holder's express written permission. Additionally, content may not be used with any artificial intelligence tools or machine learning technologies. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)
Databáze: Biomedical Index
Popis
Abstrakt:We propose a category-independent method to produce a bag of regions and rank them, such that top-ranked regions are likely to be good segmentations of different objects. Our key objectives are completeness and diversity: Every object should have at least one good proposed region, and a diverse set should be top-ranked. Our approach is to generate a set of segmentations by performing graph cuts based on a seed region and a learned affinity function. Then, the regions are ranked using structured learning based on various cues. Our experiments on the Berkeley Segmentation Data Set and Pascal VOC 2011 demonstrate our ability to find most objects within a small bag of proposed regions. [ABSTRACT FROM PUBLISHER]
ISSN:01628828
DOI:10.1109/TPAMI.2013.122