A Similarity Inference Metric for RGB-Infrared Cross-Modality Person Re-identification

Authors: Mengxi Jia, Yunpeng Zhai, Shijian Lu, Siwei Ma, Jian Zhang

IJCAI 2020 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Experimental Extensive experiments over two cross-modality re-ID datasets (SYSU-MM01 and Reg DB) show that SIM achieves significant accuracy improvement but with little extra training as compared with the state-of-the-art.
Researcher Affiliation Academia 1School of Electronic and Computer Engineering, Peking University, China 2Nanyang Technological University, Singapore 3School of Electronics Engineering and Computer Science, Peking University, China 4 Peng Cheng Laboratory, China
Pseudocode Yes Algorithm 1 Similarity Inference Metric (SIM) Input: Query-gallery similarity matrix Dq,g, gallery-gallery similarity matrix Dg,g Parameter: λ, K and α Output: SIM d SIM 1: Initialize similarity graph A(V, E) as Eq. (1). 2: %Compute SGR distance 3: for each qi, gj do 4: for gt in gj s k-nearest neighbors do 5: Calculate d(qi, gt, gj) = E(qi, gt) + E(gt, gj) 6: end for 7: Sort d(qi, gt, gj) for all gt. 8: Calculate d S(qi, gj) according to Eq. (5). 9: end for 10: %Compute MNNR distance 11: for each qi, gj do 12: Calculate d M(qi, gj) according to Eq. (7). 13: end for 14: Calculate d SIM according to Eq. (8). 15: return d SIM
Open Source Code No The paper does not provide any explicit statement or link indicating that the source code for the described methodology is publicly available.
Open Datasets Yes The proposed SIM is evaluated over two public datasets Reg DB and SYSU-MM01. Reg DB [Nguyen et al., 2017] is collected by using dual cameras (with optical and thermal sensors). SYSU-MM01 [Wu et al., 2017] is a large-scale RGB-IR re-ID dataset...
Dataset Splits No Reg DB: This dataset is randomly split into two halves, one half for training and the other half for testing. SYSU-MM01: The training set contains 19,659 RGB images and 12,792 IR images of 395 persons and the test set contains images of 96 persons. (No explicit validation set mentioned for either dataset).
Hardware Specification No No specific hardware details (such as GPU or CPU models) used for running the experiments are mentioned in the paper.
Software Dependencies No The paper mentions using ResNet-50 as a backbone network and the Adam optimizer but does not provide specific software dependencies with version numbers (e.g., PyTorch, TensorFlow, Python version).
Experiment Setup Yes During training, the input image is uniformly resized to 256 128 and traditional image augmentation is performed via random flipping and random erasing [Zhong et al., 2017b]. In addition, we use the Adam optimizer to train the model and the learning rate is set at 3.5 10 4. The whole training process consists of 200 epochs.