Image Segmentation Using Hierarchical Merge Tree

TL;DR

This paper introduces a supervised hierarchical method for image segmentation that uses a tree structure to merge regions, achieving state-of-the-art accuracy without relying on semantic priors.

Contribution

It presents a novel hierarchical approach with a tree-based model and an iterative training algorithm for improved image segmentation accuracy.

Findings

Achieves state-of-the-art region accuracy on six datasets.

Effectively emphasizes accurate boundaries through segmentation accumulation.

Demonstrates competitive performance without semantic priors.

Abstract

This paper investigates one of the most fundamental computer vision problems: image segmentation. We propose a supervised hierarchical approach to object-independent image segmentation. Starting with over-segmenting superpixels, we use a tree structure to represent the hierarchy of region merging, by which we reduce the problem of segmenting image regions to finding a set of label assignment to tree nodes. We formulate the tree structure as a constrained conditional model to associate region merging with likelihoods predicted using an ensemble boundary classifier. Final segmentations can then be inferred by finding globally optimal solutions to the model efficiently. We also present an iterative training and testing algorithm that generates various tree structures and combines them to emphasize accurate boundaries by segmentation accumulation. Experiment results and comparisons with other very recent methods on six public data sets demonstrate that our approach achieves the state-of-the-art region accuracy and is very competitive in image segmentation without semantic priors.