Empirical Risk Minimization for Metric Learning Using Privileged Information
Authors: Xun Yang, Meng Wang, Luming Zhang, Dacheng Tao
IJCAI 2016 | Conference PDF | Archive PDF | Plain Text | LLM Run Details
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Experimental | Experiment results show that by leveraging privileged information, our proposed method can achieve satisfactory performance. We have evaluated the proposed method on two real world problems: person reidentification and face verification. We conduct experiments on three real-world datasets: VIPeR [Gray and Tao, 2008], i LIDS [Zheng et al., 2009], and LFW [Huang et al., 2007]. |
| Researcher Affiliation | Academia | Xun Yang, Meng Wang, Luming Zhang, and Dacheng Tao School of Computer and Information, Hefei University of Technology, China Centre for Quantum Computation & Intelligent Systems, FEIT, University of Technology Sydney, Australia {hfutyangxun, eric.mengwang, zglumg}@gmail.com; dacheng.tao@uts.edu.au; |
| Pseudocode | Yes | Algorithm 1 ERMML+ |
| Open Source Code | No | The paper does not provide an explicit statement or link to the open-source code for the proposed method. There is a footnote with a URL to a descriptor ('http://www.micc.unifi.it/lisanti/source-code/whos/'), but this is for an external component, not the authors' own code. |
| Open Datasets | Yes | To validate the effectiveness of our method, we conduct experiments on three real-world datasets: VIPeR [Gray and Tao, 2008], i LIDS [Zheng et al., 2009], and LFW [Huang et al., 2007]. |
| Dataset Splits | Yes | The datasets are randomly divided into two parts and the testing set has p individuals. We repeat the random partition 10 times to get an average performance. The dataset is divided into 10 folds, in which each fold has 300 similar image pairs and 300 dissimilar image pairs. In this experiment, we randomly choose K folds for training and the rest is used for testing. The procedure is repeated 10 times to report an average result. |
| Hardware Specification | No | The paper does not specify the hardware used for running the experiments. |
| Software Dependencies | No | The paper mentions using a 'log loss function' and the 'Accelerated Proximal Gradient (APG) method' but does not provide specific software names with version numbers (e.g., Python, TensorFlow, PyTorch, or specific library versions). |
| Experiment Setup | Yes | For all methods, PCA is first used for dimension reduction. ERMML+ and ERMML are applied with all PCA components, since they employ the low-rank projection to obtain the PSD constrained metric. Other algorithms are applied with the first 100 dimensional PCA components. The fixed threshold is set as the mean of the squared Euclidean distances between all pairs of training instances. In the following experiments, we implement ERMML+ and ERMML using the log loss function. We extract the 3456 dimensional SIFT descriptors as the original features, which are reduced to 200 dimensions using PCA for all methods. We only consider the pairwise constraints given by the similar/dissimilar pairs. |