Multiscale Combinatorial Grouping

被引：692

作者：

Arbelaez, Pablo ^{[1
]}

Pont-Tuset, Jordi ^{[2
]}

Barron, Jonathan T. ^{[1
]}

Marques, Ferran ^{[2
]}

Malik, Jitendra ^{[1
]}

机构：

[1] Univ Calif Berkeley, Berkeley, CA 94720 USA

[2] Univ Politecn Cataluna, BarcelonaTech, Barcelona, Spain

来源：

2014 IEEE CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR) | 2014年

关键词：

D O I：

10.1109/CVPR.2014.49

中图分类号：

TP18 [人工智能理论];

学科分类号：

081104 ; 0812 ; 0835 ; 1405 ;

摘要：

We propose a unified approach for bottom-up hierarchical image segmentation and object candidate generation for recognition, called Multiscale Combinatorial Grouping (MCG). For this purpose, we first develop a fast normalized cuts algorithm. We then propose a high-performance hierarchical segmenter that makes effective use of multiscale information. Finally, we propose a grouping strategy that combines our multiscale regions into highly-accurate object candidates by exploring efficiently their combinatorial space. We conduct extensive experiments on both the BSDS500 and on the PASCAL 2012 segmentation datasets, showing that MCG produces state-of-the-art contours, hierarchical regions and object candidates.

引用

页码：328 / 335

页数：8