Notice: The reproducibility variables underlying each score are classified using an automated LLM-based pipeline, validated against a manually labeled dataset. LLM-based classification introduces uncertainty and potential bias; scores should be interpreted as estimates. Full accuracy metrics and methodology are described in Coakley et alK. L. Coakley, T. Snelleman, H. Hoos, and O. E. Gundersen, "The embrace of open science: An analysis of a decade of AI research and 56 800 conference papers," Under Review, 2026..
Bilevel Distance Metric Learning for Robust Image Recognition
Authors: Jie Xu, Lei Luo, Cheng Deng, Heng Huang
NeurIPS 2018 | Venue PDF | 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. |