# How to scale hyperparameters for quickshift image segmentation

arXiv: https://arxiv.org/abs/2201.09286 · HTML: https://mlsanity.com/paper/2201.09286/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 9 of its 28 references that are in the map.
- First posted on arXiv 23 Jan 2022.

## Builds on (most cited first, 9 of 9)

- [ImageNet Large Scale Visual Recognition Challenge](https://mlsanity.com/paper/1409.0575/) (2014)
- ["Why Should I Trust You?": Explaining the Predictions of Any Classifier](https://mlsanity.com/paper/1602.04938/) (2016)
- [The Cityscapes Dataset for Semantic Urban Scene Understanding](https://mlsanity.com/paper/1604.01685/) (2016)
- [Explaining the Explainer: A First Theoretical Analysis of LIME](https://mlsanity.com/paper/2001.03447/) (2020)
- [What does LIME really see in images?](https://mlsanity.com/paper/2102.06307/) (2021)
- [Quickshift++: Provably Good Initializations for Sample-Based Mean Shift](https://mlsanity.com/paper/1805.07909/) (2018)
- [On the Consistency of Quick Shift](https://mlsanity.com/paper/1710.10646/) (2017)
- [Modal-set estimation with an application to clustering](https://mlsanity.com/paper/1606.04166/) (2016)
- [Analysis of a Mode Clustering Diagram](https://mlsanity.com/paper/1805.04187/) (2018)

## Built on by (most cited first, 1 of 1)

- [Inpainting Insights: Elevating Visual XAI with Photorealistic Perturbations](https://mlsanity.com/paper/2607.15482/) (2026)

## Abstract (arXiv)

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.