Camera-Aware Proxies for Unsupervised Person Re-Identification

Authors: Menglin Wang, Baisheng Lai, Jianqiang Huang, Xiaojin Gong, Xian-Sheng Hua2764-2772

AAAI 2021 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Experimental Extensive experiments on three large-scale Re-ID datasets show that our proposed approach outperforms most unsupervised methods by a significant margin.
Researcher Affiliation Collaboration 1Zhejiang University, Hangzhou, China 2Alibaba Group
Pseudocode Yes Algorithm 1 Camera-aware Proxy Assisted Learning
Open Source Code Yes Code is available at: https://github.com/Terminator8758/CAP-master.
Open Datasets Yes We evaluate the proposed method on three large-scale datasets: Market-1501 (Zheng et al. 2015), Duke MTMC-re ID (Zheng, Zheng, and Yang 2017), and MSMT17 (Wei et al. 2018b).
Dataset Splits Yes Market-1501 (Zheng et al. 2015) ... It is split into three sets. The training set has 12,936 images of 751 identities, the query set has 3,368 images of 750 identities, and the gallery set contains 19,732 images of 750 identities. ... Duke MTMC-re ID (Zheng, Zheng, and Yang 2017) ... 702 identities are used for training and the rest identities are for testing. ... MSMT17 (Wei et al. 2018b) ... 32,621 images of 1041 identities are for training, the rest including 82,621 gallery images and 11,659 query images are for testing.
Hardware Specification No The paper does not specify the exact hardware (e.g., GPU/CPU models, memory) used for running the experiments.
Software Dependencies No The paper mentions software components like ResNet-50, DBSCAN, and ADAM optimizer, but does not provide specific version numbers for any software dependencies.
Experiment Setup Yes The memory updating rate µ is empirically set to be 0.2, the temperature factor τ is 0.07, the number of hard negative proxies is 50, and the balancing factor λ in Eq. (5) is 0.5. ... The initial learning rate is 0.00035 with a warmup scheme in the first 10 epochs, and is divided by 10 after each 20 epochs. The total epoch number is 50. Each training batch consists of 32 images randomly sampled from 8 proxies with 4 images per proxy. Random flipping, cropping and erasing are applied as data augmentation.