Multiscale Combinatorial Grouping for Image Segmentation and Object Proposal Generation

TL;DR

This paper introduces Multiscale Combinatorial Grouping (MCG), a unified method for hierarchical image segmentation and object proposal generation that achieves state-of-the-art results across multiple datasets.

Contribution

The paper presents a novel multiscale combinatorial grouping approach, including a fast normalized cuts algorithm and a high-performance hierarchical segmenter, improving object proposal accuracy and efficiency.

Findings

MCG achieves state-of-the-art performance on BSDS500, SegVOC12, SBD, and COCO datasets.

SCG, a faster variant, produces competitive proposals in under five seconds per image.

Extensive empirical validation demonstrates the effectiveness of the proposed methods.

Abstract

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.