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. |