Distributed Manifold Hashing for Image Set Classification and Retrieval
Authors: Xiaobo Shen, Peizhuo Song, Yun-Hao Yuan, Yuhui Zheng
AAAI 2024 | Conference PDF | Archive PDF | Plain Text | LLM Run Details
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Experimental | Extensive experiments on three benchmark datasets demonstrate that DMH achieves highly competitive accuracies in a distributed setting and provides faster classification and retrieval than state-of-the-arts. |
| Researcher Affiliation | Academia | Xiaobo Shen1, Peizhuo Song1, Yun-Hao Yuan2, Yuhui Zheng3,4* 1Nanjing University of Science and Technology 2Yangzhou University 3Qinghai Normal University 4Nanjing University of Information Science and Technology |
| Pseudocode | No | The paper does not contain structured pseudocode or algorithm blocks, but rather describes optimization steps in paragraph form with equations. |
| Open Source Code | No | The paper does not provide concrete access to source code for the methodology described, nor does it state that code is available in supplementary materials or via a specific repository link. |
| Open Datasets | Yes | To our knowledge, three large-scale image set datasets, i.e., BBT (Li et al. 2015), PB (Li et al. 2015), YTC (Kim et al. 2008) are used for experiment. The statistics of the three datasets are summarized in Table 1. |
| Dataset Splits | Yes | Table 1: Statistics of three datasets. #Samples #Classes #Training #Testing #Dim BBT 4,667 15 3,268 1,399 512 PB 9,435 20 6,602 2,828 512 YTC 1,856 47 1,484 372 900 |
| Hardware Specification | No | The paper does not provide specific hardware details (e.g., exact GPU/CPU models, processor types, or memory amounts) 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 | For the proposed method, we equally distribute the training set across all four nodes in the network to construct distributed data. The two trade-off parameters, i.e., α, υ are varied from [10 3, 103] and [0, 500] respectively. Figure 4 reports accuracies and m APs of the proposed DMH with respect to different values of the two parameters on BBT. |