Towards Generalized and Efficient Metric Learning on Riemannian Manifold

Authors: Pengfei Zhu, Hao Cheng, Qinghua Hu, Qilong Wang, Changqing Zhang

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

Reproducibility Variable Result LLM Response
Research Type Experimental In this section, we evaluate the proposed method on three tasks, including object recognition, video based face recognition and material classification. ... Table 1 shows accuracies of different methods on five datasets. ... Table 2: Comparison of training time (s) on five datasets
Researcher Affiliation Academia Pengfei Zhu, Hao Cheng, Qinghua Hu , Qilong Wang, Changqing Zhang School of Computer Science and Technology, Tianjin University, Tianjin 300350, China zhupengfei@tju.edu.cn, huqinghua@tju.edu.cn
Pseudocode Yes Algorithm 1 RMML-SPD and RMML-GM Algorithms
Open Source Code No The paper does not provide any statement about releasing their source code or a link to it.
Open Datasets Yes Datasets. We conduct experiments on five datasets, including ETH-80 [Leibe and Schiele, 2003], Flickr Material dataset [Sharan et al., 2009], and UIUC material [Liao et al., 2013], You Tube Celebrities [Kim et al., 2008], and You Tube Face dataset [Wolf et al., 2011].
Dataset Splits Yes Following the experimental settings in [Wang et al., 2012], we randomly choose 5 objects as gallery and the other 5 objects as probes in each category... Following the common setting in [Wang et al., 2012; Huang et al., 2015b], we randomly select 3 image sets per subject for gallery and 6 image sets for probes... 5000 video pairs are used to perform ten-fold cross validation tests. In each fold there are 500 pairs... We simply set λ to 0.1 on all datasets, and set t from {0.2, 0.4, 0.6, 0.8} by cross-validation on the training set.
Hardware Specification Yes The experiments are run on a PC equipped with a single Intel(R) Core(TM) i7-6700 (3.40GHz).
Software Dependencies No The paper mentions general software concepts (e.g., VGG-VD16 model, k LDA, k PLS) but does not provide specific version numbers for any programming languages, libraries, or frameworks used for implementation or experimentation.
Experiment Setup Yes Parameters setting. For metric learning on SPD manifold, we first compute mean vector µ and sample covariance S of a set of data to obtain a Gaussian descriptor... For LEML, η is tuned from 0.001 to 1000 and the value of ζ is tuned from 0.1 to 1. For GGDA, the graph parameter v is set from 1 to 10 and the size of projection matrix r is set to (c 1). Besides, its parameter β is tuned from 1e2 to 1e6. There are two parameters λ and t for RMML. We simply set λ to 0.1 on all datasets, and set t from {0.2, 0.4, 0.6, 0.8} by cross-validation on the training set.