Fast Decomposable Submodular Function Minimization using Constrained Total Variation

Authors: Senanayak Sesh Kumar Karri, Francis Bach, Thomas Pock

NeurIPS 2019 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Experimental We support our claims by showing results on graph cuts for 2D and 3D graphs. In this section, we consider the minimization of cut functions [3] that are an important examples of submodular functions. In our experiments, we consider the problem of minimizing cuts on 2D images and 3D volumetric surfaces for segmentation.
Researcher Affiliation Academia K S Sesh Kumar Data Science Institute Imperial College London, UK s.karri@imperial.ac.uk Francis Bach INRIA and Ecole normale superieure PSL Research University, Paris France. francis.bach@inria.fr Thomas Pock Institute of Computer Graphics and Vision, Graz University of Technology, Graz, Austria. pock@icg.tugraz.at
Pseudocode Yes Algorithm 1 From SFMDi to SFMC and Algorithm 2 From SFMDi to SFMCi
Open Source Code No The paper does not provide any statement or link indicating that the source code for the described methodology is publicly available.
Open Datasets No The paper mentions "2D images" and "3D volumetric surfaces" for segmentation but does not provide concrete access information (link, DOI, specific citation to a public dataset) for these datasets. It only describes their size and type.
Dataset Splits No The paper focuses on an optimization problem (submodular function minimization for graph cuts) rather than a typical machine learning task involving training and validation sets for model generalization. Therefore, it does not provide specific dataset split information (percentages, sample counts, etc.) for training, validation, or testing.
Hardware Specification No The paper does not provide specific hardware details (exact GPU/CPU models, processor types, memory amounts, or detailed computer specifications) used for running its experiments.
Software Dependencies No The paper does not provide specific ancillary software details, such as library or solver names with version numbers, needed to replicate the experiments.
Experiment Setup Yes In our approach, we have a parameter ε dependent on √ /n tα , where is the notion of diameter of the base polytope, n is the number of elements in the ground set and t is the number of iterations. In our experiments, we choose ε proportional to √ , √ /t and √ / √ t and respectively represent them by the same terms in Figure 1.