Multiscale Combinatorial Grouping
2014pp. 328–335
Citations Over TimeTop 1% of 2014 papers
Abstract
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.
Related Papers
- → Deep CNN Ensemble with Data Augmentation for Object Detection(2015)46 cited
- → Beyond ALBE/P: Language neutral form(1981)4 cited
- → PASCAL Users' forum(1979)
- → Teaching simulation with Pascal_SIM(1989)
- A Pascal-Oriented Program Maintenance Language and Its Application(1991)