Revisiting Decomposable Submodular Function Minimization with Incidence Relations

Authors: Pan Li, Olgica Milenkovic

NeurIPS 2018 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Experimental In what follows, we illustrate the performance of the newly proposed DSFM algorithms on a benchmark datasets used for MAP inference in image segmentation [9] and used for semi-supervised learning over graphs
Researcher Affiliation Academia Pan Li UIUC panli2@illinois.edu Olgica Milenkovic UIUC milenkov@illinois.edu
Pseudocode Yes Algorithm 1: Parallel RCDM for Solving (4)
Open Source Code Yes The code for this work can be found in https://github.com/lipan00123/DSFM-with-incidence-relations.
Open Datasets Yes We used two images oct and smallplant adopted from [14]2. ... 2Downloaded from the website of Professor Stefanie Jegelka: http://people.csail.mit.edu/stefje/code.html
Dataset Splits No The paper does not explicitly provide training/test/validation dataset splits, specific percentages, or sample counts needed to reproduce the experiment.
Hardware Specification No The paper does not explicitly describe the hardware used to run its experiments, such as specific GPU/CPU models, memory details, or cloud resources.
Software Dependencies No The paper does not provide specific version numbers for software components like programming languages, libraries, or solvers.
Experiment Setup Yes In our case, as we are only concerned with the convergence rate of the algorithm, we fix τ = 0.1.