Multiscale Combinatorial Grouping
Pablo Arbeláez, Jordi Pont-Tuset, Jon Barron et al. · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · 2014
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.
Cited by 1,139 works. doi:10.1109/cvpr.2014.49
Authors
References
- Histograms of Oriented Gradients for Human Detection
- Object Detection with Discriminatively Trained Part-Based Models
- Robust Real-Time Face Detection
- Efficient Graph-Based Image Segmentation
- Contour Detection and Hierarchical Image Segmentation
- Segmentation as selective search for object recognition
- Semantic Segmentation with Second-Order Pooling
- Measuring the Objectness of Image Windows
- Learning to detect natural image boundaries using local brightness, color, and texture cues
- CPMC: Automatic Object Segmentation Using Constrained Parametric Min-Cuts