Euler Sparse Representation for Image Classification

Authors: Yang Liu, Quanxue Gao, Jungong Han, Shujian Wang

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

Reproducibility Variable Result LLM Response
Research Type Experimental Extensive experimental results illustrate that Euler SRC outperforms traditional SRC and achieves better performance for image classification.
Researcher Affiliation Academia Yang Liu,1 Quanxue Gao,1 Jungong Han,2 Shujian Wang 1 1State Key Laboratory of Integrated Services Networks, Xidian University, Xi an, China 2School of Computing and Communications, Lancaster University, United Kingdom
Pseudocode Yes According to the fixed point iteration algorithm and Eq. (16), we summarize the pseudo code for solving the objective function (7) in Algorithm 1. Algorithm 1: Euler SRC algorithm
Open Source Code No The paper does not include any statement or link indicating that the source code for the described methodology is publicly available.
Open Datasets Yes The AR database (Martinez 1998); The COIL20 database (Nene et al. 1996); The CMU PIE database (Sim, Baker, and Bsat 2002); The LFWCrop database (Sanderson and Lovell 2009; Huang et al. 2007).
Dataset Splits No The paper describes training and testing splits for various datasets (e.g., 960 training images and 1440 testing images for AR Experiment 1, 90% training for LFWCrop), but it does not explicitly define or refer to a separate "validation" dataset split.
Hardware Specification No The paper does not provide any specific details about the hardware used to run the experiments, such as GPU models, CPU types, or memory.
Software Dependencies No The paper does not specify any software dependencies with version numbers (e.g., programming languages, libraries, or frameworks).
Experiment Setup Yes In the experiments, α = 0.5, PCA and down-sampling are selected as preprocessing for each approach respectively, where PCA reduces dimensionality to 200. In Euler SRC, we set γ = 1.9 in the following experiments.