Bilevel Distance Metric Learning for Robust Image Recognition

Authors: Jie Xu, Lei Luo, Cheng Deng, Heng Huang

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

Reproducibility Variable Result LLM Response
Research Type Experimental Extensive experiments on various occluded datasets demonstrate the effectiveness and robustness of our method.
Researcher Affiliation Collaboration 1 School of Electronic Engineering, Xidian University, Xi an, Shaanxi, China 2 Electrical and Computer Engineering, University of Pittsburgh, USA, 3 JDDGlobal.com
Pseudocode Yes Algorithm 1 Algorithm to solve Eq. (6)
Open Source Code No The paper does not provide an explicit statement or a link to the source code for the described methodology.
Open Datasets Yes We conduct several experiments on three datasets, including NUST Robust Face database (NUST-RF) [2], OSR dataset [13] and Pub Fig database [6].
Dataset Splits Yes For all metric learners, we use 5-fold cross validation and gauge the average accuracy and standard deviation as final performance.
Hardware Specification No The paper does not provide specific hardware details (e.g., GPU/CPU models, memory) used for running the experiments.
Software Dependencies No The paper does not provide specific software dependencies with version numbers.
Experiment Setup Yes All the regularization parameters are tuned from range {10 4, 10 3, 10 2, 10 1, 1, 10, 102}. For CAP and FANTOPE methods, the parameter rank of distance matrix M is tuned from [10 : 5 : 30]. For a fair comparison, we specify 1 target neighbor for each training sample for all LMNN related methods. In testing phase, we use 1-NN method.