Towards Efficient Object Re-Identification with a Novel Cloud-Edge Collaborative Framework

Authors: Chuanming Wang, Yuxin Yang, Mengshi Qi, Huanhuan Zhang, Huadong Ma

AAAI 2025 | Venue PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Experimental Extensive experiments demonstrate that our method obviously reduces transmission overhead and significantly improves performance. 5 Experiments
Researcher Affiliation Academia The State Key Laboratory of Networking and Switching Technology Beijing University of Posts and Telecommunications
Pseudocode No The paper describes the methodology using mathematical formulations (e.g., equations 2, 3, 4, 5, 6, 7, 8, 9, 10) and descriptive text, but does not include any explicitly labeled pseudocode or algorithm blocks.
Open Source Code No The paper does not provide any explicit statement about the release of source code, a link to a code repository, or information about code in supplementary materials.
Open Datasets Yes Datasets. We mainly evaluate our proposed framework and method on the Duke MTMC-re ID (Zheng, Zheng, and Yang 2017) and Market-1501 (Zheng et al. 2015) datasets, since they are annotated with high-quality timestamp.
Dataset Splits No The paper mentions using the Duke MTMC-re ID and Market-1501 datasets for evaluation but does not specify the training, testing, or validation splits used for experiments.
Hardware Specification No The paper does not provide specific details about the hardware (e.g., GPU models, CPU models, memory specifications) used to run the experiments.
Software Dependencies No The paper mentions using Adam as an optimizer but does not provide specific software dependencies with version numbers, such as programming languages, libraries, or frameworks (e.g., Python, PyTorch, CUDA versions).
Experiment Setup Yes Hyper-parameters: To train the Da CM network, we employ Adam (Kingma and Ba 2015) as the optimizer. The initial learning rate is set to 0.01 and is reduced by 10 for every 30 epochs. γ0 and γ1 are both set to 0.01 as the default. α and β are bot set to 0.1. λ in Eq. (2) is set to 10,000 as the default. B is set to 3 C, i.e., each edge device can upload an average of three images at a time.