How to scale hyperparameters for quickshift image segmentation

TL;DR

This paper provides a theoretical analysis of a modified quickshift image segmentation algorithm, offering a heuristic for hyperparameter scaling based on image size, validated through empirical experiments.

Contribution

It introduces a theoretical framework for understanding quickshift hyperparameters and proposes a practical heuristic for their scaling with image size.

Findings

Heuristic effectively scales hyperparameters with image size

Theoretical analysis clarifies hyperparameter influence on superpixels

Empirical validation supports the proposed heuristic

Abstract

Quickshift is a popular algorithm for image segmentation, used as a preprocessing step in many applications. Unfortunately, it is quite challenging to understand the hyperparameters' influence on the number and shape of superpixels produced by the method. In this paper, we study theoretically a slightly modified version of the quickshift algorithm, with a particular emphasis on homogeneous image patches with i.i.d. pixel noise and sharp boundaries between such patches. Leveraging this analysis, we derive a simple heuristic to scale quickshift hyperparameters with respect to the image size, which we check empirically.