Semi-Supervised Classifications via Elastic and Robust Embedding
Authors: Yun Liu, Yiming Guo, Hua Wang, Feiping Nie, Heng Huang
AAAI 2017 | Conference PDF | Archive PDF | Plain Text | LLM Run Details
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Experimental | Extensive experiments have been performed on both single-label image categorizations and multi-label image annotations to evaluate the new method. In all empirical results, our approach outperforms other related methods. |
| Researcher Affiliation | Academia | 1Department of Computer Science and Engineering, University of Texas at Arlington, Texas, USA 2Computer Science Department, Illinois Institute of Technology, Chicago, Illinois, USA 3Division of Computer Science, Colorado School of Mines, Colorado, USA 4School of Computer Science, OPTIMAL, Northwestern Polytechnical University, Xian 710072, Shaanxi, P. R. China |
| Pseudocode | Yes | Algorithm 1: The algorithm to solve the problem (11). Initialize x ; while not converge do 1. For each i, calculate si according to Eq.(13). ; 2. Update x by solving the problem (15) ; end Output: x. |
| Open Source Code | No | The paper references a third-party software package, 'SVMlight software package', but does not provide any link or statement about releasing the source code for their own described methodology. |
| Open Datasets | Yes | We experiment with two single-label image data sets (Caltech-101 and MSRC-v1) for four image classification tasks (following (Dueck and Frey 2007; Lee and Grauman 2009)), which are broadly used in computer vision studies. |
| Dataset Splits | No | The paper states, 'A 5-fold cross-validation is conducted on the labeled data to fine tune the parameters of the compared methods.' and 'For each of the four classification tasks from the two image data sets, we randomly select 20% images as labeled data and the rest as unlabeled data'. However, it does not explicitly provide fixed train/validation/test splits with percentages or sample counts for reproducibility. |
| Hardware Specification | No | The paper does not provide specific details about the hardware (e.g., CPU, GPU models, memory) used for running the experiments. |
| Software Dependencies | No | The paper mentions 'SVMlight software package' but does not specify a version number. No other specific software dependencies with version numbers are provided. |
| Experiment Setup | Yes | The proposed method has two parameters α and β in Eq. (9). Upon some preliminary tests, we bound the parameters in the ranges of 1 α 10 and 0.01 β 0.1. |