(Probably) Concave Graph Matching

Authors: Haggai Maron, Yaron Lipman

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

Reproducibility Variable Result LLM Response
Research Type Experimental 5 Experiments
Researcher Affiliation Academia Haggai Maron Weizmann Institute of Science Rehovot, Israel haggai.maron@weizmann.ac.il Yaron Lipman Weizmann Institute of Science Rehovot, Israel yaron.lipman@weizmann.ac.il
Pseudocode Yes Algorithm 1: Frank-Wolfe algorithm.
Open Source Code No The paper does not provide concrete access to source code for the methodology described in this paper.
Open Datasets Yes SHREC07 (Giorgi et al., 2007) shape matching benchmark
Dataset Splits No The paper mentions using datasets like SHREC07 and Model Net10 and a 'protocol of Kim et al. (2011)', but does not explicitly provide specific train/validation/test dataset split information within its main text.
Hardware Specification Yes 150msec for n = 200 with Algorithm 1, and 16sec with Algorithm 2, both on a single CPU
Software Dependencies No The paper does not provide specific ancillary software details with version numbers.
Experiment Setup Yes On each shape, we sampled k = 8 points using farthest point sampling and randomized s = 2000 initializations of subsets of l = 3 points. In this stage, we use n = 300 points. We then up-sampled to n = 1500 using the exact algorithm with initialization using our n = 300 best result.