DIMGNet: A Transformer-Based Network for Pedestrian Reidentification With Multi-Granularity Information Mutual Gain
- 15 January 2024
- journal article
- research article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Multimedia
- Vol. 26 (15209210) , 6513-6528
Abstract
Pedestrian reidentification (ReID) is a challenging task that involves identifying and retrieving specific pedestrians across different cameras and scenes. This problem has significant implications for security surveillance, and has thus received substantial attention in recent years. However, traditional convolutional neural networks (CNNs) have limited receptive fields and cannot capture global information. Moreover, transformer networks, which excel in long-range feature capture, are prone to accuracy degradation due to loss of details. To address these limitations, we propose a transformer-based pedestrian ReID network with double-branch information mutual gain (DIMGNet), which leverages hierarchical parallel levels to support multi-granularity feature information mutual gain. Our model also incorporates an auxiliary camera information (ACI) module to improve feature representation ability. We further embed a cross-attention mechanism into the architecture to enhance mutual gain between multi-granularity features and improve feature discrimination. Finally, we introduce a shuffling technique to increase the robustness of the extracted features. We evaluate the proposed method on several benchmark datasets, including Market-1501[1], MSMT17[2], DukeMTMC-reID [3], and Occluded-Duke [4], achieving $mAP$ values of 90.7%, 68.4%, 83.7%, and 60.6%, respectively. Our method outperforms most state-of-the-art methods, demonstrating the effectiveness of our method. The code will be publicly released at https://github.com/ZhenlinZhu/DIMGNet .Keywords
Funding Information
- National Natural Science Foundation of China (61502164, 62176097)
- Natural Science Foundation of Hunan Province (2020JJ4057)
- Key Research and Development Program of Changsha Science and Technology Bureau (kq2004050)
- Scientific Research Foundation of the Education Department of Hunan Province of China (21A0052)
This publication has 59 references indexed in Scilit:
- ResT-ReID: Transformer block-based residual learning for person re-identificationPattern Recognition Letters, 2022
- Person re-identification based on multi-scale feature learningKnowledge-Based Systems, 2021
- Identity-Guided Human Semantic Parsing for Person Re-identification2020
- Guided Saliency Feature Learning for Person Re-identification in Crowded Scenes2020
- Related Attention Network for Person Re-Identification2019
- Mancs: A Multi-task Attentional Network with Curriculum Sampling for Person Re-Identification2018
- Deep Transfer Learning for Person Re-Identification2018
- Equidistance constrained metric learning for person re-identificationPattern Recognition, 2018
- Performance Measures and a Data Set for Multi-target, Multi-camera Tracking2016
- A Siamese Long Short-Term Memory Architecture for Human Re-identification2016