Finding Median Point-Set Using Earth Mover’s Distance
Authors: Hu Ding, Jinhui Xu
AAAI 2014 | Conference PDF | Archive PDF | Plain Text | LLM Run Details
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Experimental | We evaluate the performance of our technique for prototype reconstruction on a random dataset and a benchmark dataset, handwriting Chinese characters. Experiments suggest that our technique considerably outperforms the existing graph-based methods. |
| Researcher Affiliation | Academia | Hu Ding and Jinhui Xu Computer Science and Engineering, State University of New York at Buffalo {huding, jinhui}@buffalo.edu |
| Pseudocode | Yes | Algorithm 1 Median point-set (outline) Input: {P1, , Pn} and m Z+. repeat 1. Dynamic step. 2. Static step, with the following inner loop: (a) Location updating. (b) Weight updating. until The objective value becomes stable. |
| Open Source Code | No | The paper does not provide any explicit statement or link regarding the availability of open-source code for the described methodology. |
| Open Datasets | Yes | We test our prototype reconstruction algorithm (from Section 4) on two datasets: a random dataset and a benchmark dataset, handwriting Chinese characters (KAIST Hanja DB2 database). |
| Dataset Splits | No | The paper describes how random datasets and Chinese character datasets were generated and used for evaluation, but it does not specify explicit training, validation, and test splits for a machine learning model's training process. |
| Hardware Specification | No | The paper does not provide specific details about the hardware (e.g., CPU, GPU models, memory) used to run the experiments. |
| Software Dependencies | No | The paper mentions algorithms like k-means clustering (using Lloyd's algorithm) and solving linear programming problems, but it does not specify any software dependencies with version numbers (e.g., Python, PyTorch, CPLEX versions). |
| Experiment Setup | Yes | We set the value of k between 20 and 40. To measure the performance, we compute the EMD between the output prototype and the original character (ground truth). Figure 4c shows the results under different noise levels. |