Modality-aware Style Adaptation for RGB-Infrared Person Re-Identification

Authors: Ziling Miao, Hong Liu, Wei Shi, Wanlu Xu, Hanrong Ye

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

Reproducibility Variable Result LLM Response
Research Type Experimental Experimental results on two datasets SYSU-MM01 and Reg DB show that MSA achieves significant improvements with little extra computation cost and outperforms the state-of-the-art methods.
Researcher Affiliation Academia 1Key Laboratory of Machine Perception, Peking University, Shenzhen Graduate School, Shenzhen, China 2Department of Computer Science and Engineering, The Hong Kong University of Science and Technology, Hong Kong
Pseudocode Yes Algorithm 1 Multi-modality collaborative learning of MSA Input: RGB images:Xrgb, IR images: Xir Parameter: α, β, γ Output: Configurations of MSA 1: Initialize the parameters of F, D and C 2: for each xrgb, xir do 3: Generate xr2i, xi2r using Eq. (1) 4: for each triplet of {xrgb, xr2i, xir} do 5: Calculate LSSL1, LSSL+1 using Eq. (4), (8). 6: end for 7: for each triplet of {xir, xi2r, xrgb} do 8: Calculate LSSL2, LSSL+2 using Eq. (4), (8). 9: end for 10: Limg = α(LSSL1 + LSSL2) β(LSSL+1 + LSSL+2) 11: for each {xrgb, xir, xr2i, xi2r} do 12: Calculte F(rgb), F(ir), F(r2i), F(i2r) 13: Calculte Lid 14: Calculte Lmmtri using Eq. (10). 15: end for 16: Ltotal = Limg + γLmmtri + Lid 17: end for
Open Source Code No The paper does not provide an explicit statement or link for open-source code availability.
Open Datasets Yes Datasets. (1) SYSU-MM01 [Wu et al., 2017] is a large-scale and challenging dataset, containing 491 identities with 30,071 RGB images and 15,792 IR images. (2) Reg DB [Nguyen et al., 2017] contains 412 identities, which has 10 RGB images and 10 thermal images.
Dataset Splits No The paper describes dividing datasets into training and testing sets ('395 persons...are divided into the training set, and 96 persons are divided into the testing set.' for SYSU-MM01 and 'The dataset is randomly divided into two halves, training and testing set' for Reg DB), but does not specify a separate 'validation' split or its size/percentage.
Hardware Specification No The paper does not provide specific hardware details (e.g., GPU/CPU models, memory amounts) used for running its experiments.
Software Dependencies No The Res Net-50 [He et al., 2016] with pre-trained parameters on Image Net [Krizhevsky et al., 2012] is taken as our backbone... The Adam optimizer is used to guide the training process in 60 epochs.
Experiment Setup Yes During training, we randomly select six identities with four RGB images and four IR images sampled for each identity. We also adopt the random erasing [Lu et al., 2020] for data augmentation. The Adam optimizer is used to guide the training process in 60 epochs. The λ in Lmmtri is set to 0.5. And the trade-off hyperparameters α, β and γ are set to 1:1:1 and 13:10:7 separately on SYSU-MM01 and Reg DB datasets.