Hierarchical Superpixel Segmentation via Structural Information Theory

TL;DR

This paper introduces SIT-HSS, a hierarchical superpixel segmentation method that leverages structural information theory to incorporate global graph information, resulting in improved segmentation quality over existing methods.

Contribution

The paper proposes a novel graph construction and hierarchical partitioning strategy based on 1D and 2D structural entropy, enhancing superpixel segmentation by capturing global graph information.

Findings

Outperforms state-of-the-art unsupervised superpixel algorithms on benchmark datasets.

Uses a new graph construction strategy based on 1D structural entropy.

Employs a 2D SE-guided hierarchical merging process.

Abstract

Superpixel segmentation is a foundation for many higher-level computer vision tasks, such as image segmentation, object recognition, and scene understanding. Existing graph-based superpixel segmentation methods typically concentrate on the relationships between a given pixel and its directly adjacent pixels while overlooking the influence of non-adjacent pixels. These approaches do not fully leverage the global information in the graph, leading to suboptimal segmentation quality. To address this limitation, we present SIT-HSS, a hierarchical superpixel segmentation method based on structural information theory. Specifically, we first design a novel graph construction strategy that incrementally explores the pixel neighborhood to add edges based on 1-dimensional structural entropy (1D SE). This strategy maximizes the retention of graph information while avoiding an overly complex graph structure. Then, we design a new 2D SE-guided hierarchical graph partitioning method, which iteratively merges pixel clusters layer by layer to reduce the graph's 2D SE until a predefined segmentation scale is achieved. Experimental results on three benchmark datasets demonstrate that the SIT-HSS performs better than state-of-the-art unsupervised superpixel segmentation algorithms. The source code is available at \url{https://github.com/SELGroup/SIT-HSS}.