Feature Selection Guided Auto-Encoder

Authors: Shuyang Wang, Zhengming Ding, Yun Fu

AAAI 2017 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Experimental Experiments on several benchmarks demonstrate our method s superiority over state-of-the-art approaches. We evaluate the proposed FSAE method through data classification on three benchmark datasets, including COIL100 (Nayar, Nene, and Murase 1996), Caltech101 (Fei-Fei, Fergus, and Perona 2007) and CMUPIE (Sim, Baker, and Bsat 2002).
Researcher Affiliation Academia Shuyang Wang,1 Zhengming Ding,1 Yun Fu1,2 1Department of Electrical & Computer Engineering, 2College of Computer & Information Science, Northeastern University, Boston, MA, USA {shuyangwang, allanding, yunfu}@ece.neu.edu
Pseudocode Yes Algorithm 1: Optimization for trace-ratio problem
Open Source Code No The paper does not provide an explicit statement or link to open-source code for the described methodology.
Open Datasets Yes We evaluate the proposed FSAE method through data classification on three benchmark datasets, including COIL100 (Nayar, Nene, and Murase 1996), Caltech101 (Fei-Fei, Fergus, and Perona 2007) and CMUPIE (Sim, Baker, and Bsat 2002).
Dataset Splits No 10 images per object are randomly selected to form the training set, the rest images for test. we train on 10, 15, 25, and 30 random selected samples per category and test on the rest. The paper describes training and testing splits but does not explicitly mention a separate validation set.
Hardware Specification No The paper does not provide any specific hardware details used for running the experiments.
Software Dependencies No The paper does not provide specific software dependencies with version numbers.
Experiment Setup Yes The layersize setting for all AE based methods is [500, 100]. Specifically, λ is set as 2 10 3 for COIL100, 5 10 3 for Caltech101, 3 10 3 for CMU PIE. For selected feature size, we set it as 50% of the original hidden layer size for all the experiments, and we will analyze the impact of selection ratio. The random split is repeated 20 times, and the average results are reported with standard deviations.