Multiscale Combinatorial Grouping for Image Segmentation and Object Proposal Generation
This work addresses the need for accurate and efficient object proposal generation in computer vision, offering a unified approach that is incremental over existing segmentation methods.
The authors tackled the problem of generating hierarchical image segmentations and object proposals by introducing Multiscale Combinatorial Grouping (MCG), which achieved state-of-the-art results on multiple datasets like BSDS500 and COCO.
We propose a unified approach for bottom-up hierarchical image segmentation and object proposal 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 proposals by exploring efficiently their combinatorial space. We also present Single-scale Combinatorial Grouping (SCG), a faster version of MCG that produces competitive proposals in under five second per image. We conduct an extensive and comprehensive empirical validation on the BSDS500, SegVOC12, SBD, and COCO datasets, showing that MCG produces state-of-the-art contours, hierarchical regions, and object proposals.