How to scale hyperparameters for quickshift image segmentation
This work addresses a specific problem in image segmentation for researchers and practitioners, but it is incremental as it builds on existing quickshift methods.
The paper tackles the challenge of understanding and scaling hyperparameters in the quickshift image segmentation algorithm, deriving a heuristic based on theoretical analysis of a modified version and validating it empirically.
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.