Learning Coarse-to-Fine Structured Feature Embedding for Vehicle Re-Identification
Authors: Haiyun Guo, Chaoyang Zhao, Zhiwei Liu, Jinqiao Wang, Hanqing Lu
AAAI 2018 | Conference PDF | Archive PDF | Plain Text | LLM Run Details
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Experimental | Experimental results on Vehicle-1M and Vehicle ID demonstrate the superiority of our proposed approach. |
| Researcher Affiliation | Academia | National Laboratory of Pattern Recognition, Institute of Automation University of Chinese Academy of Sciences, Beijing, China, 100190 {haiyun.guo, chaoyang.zhao, zhiwei.liu, jqwang, luhq}@nlpr.ia.ac.cn |
| Pseudocode | No | The paper does not contain any pseudocode or algorithm blocks. |
| Open Source Code | No | The paper does not provide an explicit statement or link for the open-source code of the described methodology. The provided URL is for the dataset, not the code. |
| Open Datasets | Yes | The paper introduces Vehicle-1M, stating ‘Available at http://www.nlpr.ia.ac.cn/iva/homepage/jqwang/Vehicle1M.htm.’ It also utilizes the Vehicle ID dataset, previously released and commonly used for vehicle re-ID. |
| Dataset Splits | No | The paper mentions using a ‘validation set’ during parameter tuning (‘From the output loss value on the validation set we found the classification loss value...’), but it does not provide specific details on its size, proportion, or how it was split from the main dataset for reproduction. |
| Hardware Specification | No | The paper does not provide specific details about the hardware used to run the experiments, such as GPU models, CPU types, or memory. |
| Software Dependencies | No | The paper does not provide specific software dependency details with version numbers (e.g., Python version, PyTorch/TensorFlow versions, CUDA version). |
| Experiment Setup | Yes | The paper specifies several hyperparameters including distance margins (Mc = Mf = 0.2), K1 = 10, K2 = 3, mini-batch size = 150, and weighting values for loss terms (α = 100, β = 1000, γ = 10). |