Resolution-invariant Person Re-Identification

Authors: Shunan Mao, Shiliang Zhang, Ming Yang

IJCAI 2019 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Experimental We evaluate our methods on five datasets containing person images at a large range of resolutions, where our methods show substantial superiority to existing solutions.
Researcher Affiliation Collaboration Shunan Mao1 , Shiliang Zhang1 and Ming Yang2 1Peking University 2Horizon Robotics, Inc {snmao, slzhang.jdl}@pku.edu.cn, ming.yang@horizon-robotics.com
Pseudocode No The paper does not contain any pseudocode or algorithm blocks.
Open Source Code No The paper does not provide any statement or link regarding the availability of open-source code for the described methodology.
Open Datasets Yes CAVIAR [Cheng et al., 2011] contains 1220 images of 72 identities. MLR-VIPe R and MLR-CUHK03 are constructed on VIPe R [Gray and Tao, 2008] and CUHK03 [Li et al., 2014] datasets. VR-Market1501 and VR-MSMT17 are constructed by us based on Market1501 [Zheng et al., 2015] and MSMT [Wei et al., 2018], respectively.
Dataset Splits No The paper mentions training and testing sets for various datasets but does not explicitly describe or refer to a validation set split.
Hardware Specification Yes All of our experiments are implemented with GTX 1080Ti GPU, Intel i7 CPU, and 128GB memory.
Software Dependencies No The paper states: "Our network is trained on Py Torch by Stochastic Gradient Descent (SGD)." It mentions PyTorch but does not provide a specific version number.
Experiment Setup Yes We fix hyperparameters as α = 1, β = 0.1 for all datasets. Each step has 60 epoches and the batch size is set as 32. The initial learning rate is set as 0.01 at the first two steps and 0.001 at the final step. The learning rate is reduced ten times after 30 epoches.