Multiscale Combinatorial Grouping. Arbelaez, P., Pont-Tuset, J., Barron, J., Marques, F., & Malik, J. In 2014 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pages 328--335, June, 2014. 00054
doi  abstract   bibtex   
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.
@inproceedings{ arbelaez_multiscale_2014,
  title = {Multiscale {Combinatorial} {Grouping}},
  doi = {10.1109/CVPR.2014.49},
  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.},
  booktitle = {2014 {IEEE} {Conference} on {Computer} {Vision} and {Pattern} {Recognition} ({CVPR})},
  author = {Arbelaez, P. and Pont-Tuset, J. and Barron, J. and Marques, F. and Malik, J.},
  month = {June},
  year = {2014},
  note = {00054},
  pages = {328--335}
}

Downloads: 0