Person Re-Identification by Deep Joint Learning of Multi-Loss Classification

Authors: Wei Li, Xiatian Zhu, Shaogang Gong

IJCAI 2017 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Experimental Extensive comparative evaluations demonstrate the advantages of this new JLML model for person re-id over a wide range of state-of-the-art re-id methods on four benchmarks (VIPe R, GRID, CUHK03, Market-1501).
Researcher Affiliation Academia Queen Mary University of London, London E1 4NS, UK
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 to its open-source code.
Open Datasets Yes For evaluation, we used four benchmarking re-id datasets, VIPe R [Gray and Tao, 2008], GRID [Loy et al., 2009], CUHK03 [Li et al., 2014], and Market-1501 [Zheng et al., 2015].
Dataset Splits Yes On VIPe R, we split randomly the whole population (632 people) into two halves: One for training (316) and another for testing (316). We repeated 10 trials of random people splits and used the averaged results. On GRID, the training/test split was 125/125 with 775 distractor people included in the test gallery. We used the benchmarking 10 people splits [Loy et al., 2009] and the averaged performance. On CUHK03, following [Li et al., 2014] we repeated 20 times of random 1260/100 training/test splits and reported the averaged accuracies under the single-shot evaluation setting. On Market-1501, we used the standard training/test split (750/751) [Zheng et al., 2015].
Hardware Specification No The paper does not specify the hardware used for experiments (e.g., GPU/CPU models, memory).
Software Dependencies No The paper mentions using the "Caffe framework [Jia et al., 2014]" but does not provide specific version numbers for Caffe or any other software dependencies.
Experiment Setup Yes Table 4: JLML training parameters. BLR: base learning rate; LRP: learning rate policy; MOT: momentum; IT: iteration; BS: batch size. [...] We also adopted the stepped learning rate policy, e.g. dropping the learning rate by a factor of 10 every 100K iterations for JLML pre-training and every 20K iterations for JLML training.