How to scale hyperparameters for quickshift image segmentation
Not on the map. Why?
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.
Key facts. Cited by 1 paper in the map (data through 13 Oct 2026). Builds on 9 of its 28 references that are in the map. First posted on arXiv 23 Jan 2022.
Builds on
9 of 28 references.
References · 9
- 2014ImageNet Large Scale Visual Recognition Challengecited by 8,476
- 2016"Why Should I Trust You?": Explaining the Predictions of Any Classifiercited by 5,055
- 2016The Cityscapes Dataset for Semantic Urban Scene Understandingcited by 4,435
- 2020Explaining the Explainer: A First Theoretical Analysis of LIMEcited by 89
- 2021What does LIME really see in images?cited by 21
- 2018Quickshift++: Provably Good Initializations for Sample-Based Mean Shiftcited by 14
- 2017On the Consistency of Quick Shiftcited by 7
- 2016Modal-set estimation with an application to clusteringcited by 3
- 2018Analysis of a Mode Clustering Diagramcited by 1
Built on by
Citing papers per year: 2026: 1.
1 paper.