Uncertainty in minimum cost multicuts for image and motion segmentation

Amirhossein Kardoost, Margret Keuper
Proceedings of the Thirty-Seventh Conference on Uncertainty in Artificial Intelligence, PMLR 161:2029-2038, 2021.

Abstract

The minimum cost lifted multicut approach has proven practically good performance in a wide range of applications such as image decomposition, mesh segmentation, multiple object tracking and motion segmentation. It addresses such problems in a graph-based model, where real valued costs are assigned to the edges between entities such that the minimum cut decomposes the graph into an optimal number of segments. Driven by a probabilistic formulation of minimum cost multicuts, we provide a measure for the uncertainties of the decisions made during the optimization. We argue that the access to such uncertainties is crucial for many practical applications and conduct an evaluation by means of sparsifications on three different, widely used datasets in the context of image decomposition (BSDS-500) and motion segmentation (DAVIS$_{2016}$ and FBMS$_{59}$) in terms of variation of information (VI) and Rand index (RI).

Cite this Paper

BibTeX
@InProceedings{pmlr-v161-kardoost21a, title = {Uncertainty in minimum cost multicuts for image and motion segmentation}, author = {Kardoost, Amirhossein and Keuper, Margret}, booktitle = {Proceedings of the Thirty-Seventh Conference on Uncertainty in Artificial Intelligence}, pages = {2029--2038}, year = {2021}, editor = {de Campos, Cassio and Maathuis, Marloes H.}, volume = {161}, series = {Proceedings of Machine Learning Research}, month = {27--30 Jul}, publisher = {PMLR}, pdf = {https://proceedings.mlr.press/v161/kardoost21a/kardoost21a.pdf}, url = {https://proceedings.mlr.press/v161/kardoost21a.html}, abstract = {The minimum cost lifted multicut approach has proven practically good performance in a wide range of applications such as image decomposition, mesh segmentation, multiple object tracking and motion segmentation. It addresses such problems in a graph-based model, where real valued costs are assigned to the edges between entities such that the minimum cut decomposes the graph into an optimal number of segments. Driven by a probabilistic formulation of minimum cost multicuts, we provide a measure for the uncertainties of the decisions made during the optimization. We argue that the access to such uncertainties is crucial for many practical applications and conduct an evaluation by means of sparsifications on three different, widely used datasets in the context of image decomposition (BSDS-500) and motion segmentation (DAVIS$_{2016}$ and FBMS$_{59}$) in terms of variation of information (VI) and Rand index (RI).} }
Endnote
%0 Conference Paper %T Uncertainty in minimum cost multicuts for image and motion segmentation %A Amirhossein Kardoost %A Margret Keuper %B Proceedings of the Thirty-Seventh Conference on Uncertainty in Artificial Intelligence %C Proceedings of Machine Learning Research %D 2021 %E Cassio de Campos %E Marloes H. Maathuis %F pmlr-v161-kardoost21a %I PMLR %P 2029--2038 %U https://proceedings.mlr.press/v161/kardoost21a.html %V 161 %X The minimum cost lifted multicut approach has proven practically good performance in a wide range of applications such as image decomposition, mesh segmentation, multiple object tracking and motion segmentation. It addresses such problems in a graph-based model, where real valued costs are assigned to the edges between entities such that the minimum cut decomposes the graph into an optimal number of segments. Driven by a probabilistic formulation of minimum cost multicuts, we provide a measure for the uncertainties of the decisions made during the optimization. We argue that the access to such uncertainties is crucial for many practical applications and conduct an evaluation by means of sparsifications on three different, widely used datasets in the context of image decomposition (BSDS-500) and motion segmentation (DAVIS$_{2016}$ and FBMS$_{59}$) in terms of variation of information (VI) and Rand index (RI).
APA
Kardoost, A. & Keuper, M.. (2021). Uncertainty in minimum cost multicuts for image and motion segmentation. Proceedings of the Thirty-Seventh Conference on Uncertainty in Artificial Intelligence, in Proceedings of Machine Learning Research 161:2029-2038 Available from https://proceedings.mlr.press/v161/kardoost21a.html.

Related Material