Superpixels: An evaluation of the state-of-the-art

By David Stutz, Alexander Hermans, Bastian Leibe. Computer Vision and Image Understanding, 2016

520 citations recorded by the source corpus.

Abstract Superpixels group perceptually similar pixels to create visually meaningful entities while heavily reducing the number of primitives for subsequent processing steps. As of these properties, superpixel algorithms have received much attention since their naming in 2003 (Ren and Malik, 2003). By today, publicly available superpixel algorithms have turned into standard tools in low-level vision. As such, and due to their quick adoption in a wide range of applications, appropriate benchmarks are crucial for algorithm selection and comparison. Until now, the rapidly growing number of algorithms as well as varying experimental setups hindered the development of a unifying benchmark. We present a comprehensive evaluation of 28 state-of-the-art superpixel algorithms utilizing a benchmark focussing on fair comparison and designed to provide new insights relevant for applications. To this end, we explicitly discuss parameter optimization and the importance of strictly enforcing connectivity. Furthermore, by extending well-known metrics, we are able to summarize algorithm performance independent of the number of generated superpixels, thereby overcoming a major limitation of available benchmarks. Furthermore, we discuss runtime, robustness against noise, blur and affine transformations, implementation details as well as aspects of visual quality. Finally, we present an overall ranking of superpixel algorithms which redefines the state-of-the-art and enables researchers to easily select appropriate algorithms and the corresponding implementations which themselves are made publicly available as part of our benchmark at http://www.davidstutz.de/projects/superpixel-benchmark/ .

Subfields: Computer Vision and Pattern Recognition, Media Technology

View Paper: https://www.semanticscholar.org/paper/f4d62a0c053da65ad5888547b3c9e3b18361cb44

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Computer Vision and Pattern Recognition

In Media Technology

Citations in the corpus

Adaptive Prototype Learning and Allocation for Few-Shot Segmentation (2021, methodology): “For more details about traditional and existing methods on superpixels, please refer to [1, 26].”
The explanation game: a formal framework for interpretable machine learning (2020, unknown): “For instance, Bob may coarsen a set of genes into a smaller collection of biological pathways (Sanguinetti and Huynh-Thu 2018), or transform pixels into super-pixels (Stutz et al. 2018).”
Regional Multi-Scale Approach for Visually Pleasing Explanations of Deep Neural Networks (2018, background): “We refer the reader to [21] for a survey of the issues related to superpixel segmentation.”
Multi-Scale Representation Learning on Proteins (2022, methodology): “, 2011] outperforms previous methods across different tasks [Stutz et al., 2018] and achieves the desired properties of molecular superpixels.”
Self-Supervised Representation Learning for Remote Sensing Image Change Detection Based on Temporal Prediction (2020, methodology): “In terms of this, our method is similar to image segmentation that merges homogeneous regions and divides the heterogeneous regions in an image such as superpixel-based [32,33], watershed-based [34,35], and level set segmentation methods [36,37].”