Robust Metric Learning on Grassmann Manifolds with Generalization Guarantees
Authors: Lei Luo, Jie Xu, Cheng Deng, Heng Huang4480-4487
AAAI 2019 | Conference PDF | Archive PDF | Plain Text | LLM Run Details
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Experimental | Experiments on six benchmark datasets clearly show that the proposed method achieves consistent improvements in discrimination accuracy, in comparison to state-of-the-art methods. |
| Researcher Affiliation | Collaboration | 1Electrical and Computer Engineering, University of Pittsburgh, USA 2School of Electronic Engineering, Xidian University, Xian, Shanxi, China, 3JDDGlobal.com |
| Pseudocode | Yes | Algorithm 1 RLMNN via Iteratively Reweighted Method |
| Open Source Code | No | The paper does not provide concrete access to source code for the methodology described. |
| Open Datasets | Yes | In this section, we evaluate the effectiveness of our method on six standard databases, including LFW database (Huang et al. 2007), Pub Fig database (Kumar et al. 2009), You Tube Face Database (Wolf, Hassner, and Maoz 2011), OSR database (Parikh and Grauman 2011) and Highway Traffic Database (Chan and Vasconcelos 2008). |
| Dataset Splits | Yes | The You Tube Face (YTF) (Wolf, Hassner, and Maoz 2011) contains 3,425 videos of 1,595 different persons collected from the You Tube website. In this database, there exist large variations in pose, illumination, and expression in each video sequence. We follow the standard evaluation protocol (Wolf, Hassner, and Maoz 2011) to perform standard, ten-fold, cross validation, pairmatching tests. [...] 30 images for each category are chosen as training data, and other images are used as testing data. The training data is randomly selected and this procedure is repeated 5 times. |
| Hardware Specification | No | The paper does not provide specific hardware details (e.g., GPU/CPU models, processor types) used for running its experiments. |
| Software Dependencies | No | The paper does not provide specific ancillary software details (e.g., library or solver names with version numbers) needed to replicate the experiment. |
| Experiment Setup | Yes | We set λ = 0.1, µ = 0.5, η = 0.8 and ϱ = 0.1 in our method. |