Multi-Level Metric Learning via Smoothed Wasserstein Distance

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

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

Reproducibility Variable Result LLM Response
Research Type Experimental Experimental evaluations on four standard databases show that our method obviously outperforms other state-of-the-art methods.
Researcher Affiliation Collaboration 1 School of Electronic Engineering, Xidian University, Xi an 710071, China 2 Electrical and Computer Engineering, University of Pittsburgh, PA, 15261, USA
Pseudocode Yes Algorithm 1 Optimization Algorithm for solving Problem (13)
Open Source Code No No explicit statement or link is provided for open-source code for the methodology described in this paper.
Open Datasets Yes We use two challenge person re-identification datasets at multi-shot scenario, i.e., PRID 2011 dataset [Hirzer et al., 2011] and i LIDSVID dataset [Office, 2008]. Kin Face W-II dataset... [Lu et al., 2014]. Traffic video database... [Chan and Vasconcelos, 2005].
Dataset Splits Yes Experiment Settings: In the experiment, we split each dataset into two folds. In each time, one fold of data is for training and the other fold is used as testing data. As a benchmark for comparison, we use the pre-specified training/testing split, which is generated for 5-fold cross validation [Lu et al., 2014].
Hardware Specification No No specific hardware details (e.g., GPU/CPU models, memory amounts, or detailed computer specifications) used for running the experiments are mentioned.
Software Dependencies No No specific software dependencies, including library names with version numbers, are mentioned.
Experiment Setup Yes In our method, we set ρ0 = 1, and ρt = 1 C , t = 1, , C. For LMNN with capped trace norm and Fantope norm methods, the regularization parameters are tuned from range {10 4, 10 3, 10 2, 10 1, 1, 10, 102}, and parameter rank of matrix M is from [30 : 5 : 70].