Single Camera Training for Person Re-Identification
Authors: Tianyu Zhang, Lingxi Xie, Longhui Wei, Yongfei Zhang, Bo Li, Qi Tian12878-12885
AAAI 2020 | Conference PDF | Archive PDF | Plain Text | LLM Run Details
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Experimental | In experiments, MCNL significantly boosts Re ID accuracy in the SCT setting, which paves the way of fast deployment of Re ID systems with good performance on new target scenes. and 5 Experiments |
| Researcher Affiliation | Academia | 1Beijing Key Laboratory of Digital Media, School of Computer Science and Engineering, Beihang University 2Johns Hopkins University, 3Peking University 4State Key Laboratory of Virtual Reality Technology and Systems, Beihang University 5School of Electronic Engineering, Xidian University |
| Pseudocode | No | The paper describes the Multi-Camera Negative Loss (MCNL) mathematically with equations, but it does not include a structured pseudocode block or algorithm section. |
| Open Source Code | No | The paper does not provide any statement or link indicating that the source code for the methodology is openly available. |
| Open Datasets | Yes | To evaluate the effectiveness of our proposed method, we mainly conduct experiments on two large-scale person Re ID datasets, i.e., Market-1501 (Zheng et al. 2015) and Duke MTMC-re ID (Zheng, Zheng, and Yang 2017b). |
| Dataset Splits | No | The paper describes the creation of new training sets (Duke-SCT and Market-SCT) and states that original testing data is kept. It does not explicitly mention or detail a separate validation dataset split for hyperparameter tuning or early stopping. |
| Hardware Specification | Yes | All experiments are conducted on two NVIDIA GTX 1080Ti GPUs. |
| Software Dependencies | No | The paper mentions using ResNet-50 as a backbone and Adam optimizer, but it does not provide specific version numbers for any programming languages, deep learning frameworks (e.g., PyTorch, TensorFlow), or other software libraries. |
| Experiment Setup | Yes | In each batch, we randomly select 8 cameras, and sample 4 identities for each selected camera. Then, we randomly sample 8 images for each identity, leading to the batch size of 256 for Duke-SCT. For Market-SCT, there are only 6 cameras in the training set. Hence, we sample 6 cameras, 5 identities for each camera, and 8 images for each identity, thus the batch size is 240 for Market-SCT. We empirically set m1 and m2 as 0.1, respectively. For baseline, we implement the batch hard triplet loss (Hermans, Beyer, and Leibe 2017)... The margin of Triplet is set to be 0.3... The learning rate ϵ is initialized as 2 10 4 and exponentially decays following the Eq. (5) proposed in (Hermans, Beyer, and Leibe 2017)... For all datasets, we update the learning rate every epoch after 100 epochs and stop training when reaching 200 epochs. |