Pose Attention-Guided Paired-Images Generation for Visible-Infrared Person Re-Identification
- 15 January 2024
- journal article
- research article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Signal Processing Letters
- Vol. 31 (10709908) , 346-350
Abstract
A key challenge of visible-infrared person re-identification (VI-ReID) comes from the modality difference between visible and infrared images, which further causes large intra-person and small inter-person distances. Most existing methods design feature extractors and loss functions to bridge the modality gap. However, the unpaired-images constrain the VI-ReID model's ability to learn instance-level alignment features. Different from these methods, in this paper, we propose a pose attention-guided paired-images generation network (PAPG) from the standpoint of data augmentation. PAPG can generate cross-modality paired-images with shape and appearance consistency with the real image to perform instance-level feature alignment by minimizing the distances of every pair of images. Furthermore, our method alleviates data insufficient and reduces the risk of VI-ReID model overfitting. Comprehensive experiments conducted on two publicly available datasets validate the effectiveness and generalizability of PAPG. Especially, on the SYSU-MM01 dataset, our method accomplishes 7.76% and 5.87% gains in Rank-1 and mAP.Keywords
Funding Information
- Macao Polytechnic University (RP/FCA-09/2023)
This publication has 28 references indexed in Scilit:
- Dual-Space Aggregation Learning and Random Erasure for Visible Infrared Person Re-IdentificationIEEE Access, 2023
- Pose-driven attention-guided image generation for person re-IdentificationPattern Recognition, 2022
- Leaning compact and representative features for cross-modality person re-identificationWorld Wide Web, 2022
- Visible-infrared person re-identification with data augmentation via cycle-consistent adversarial networkNeurocomputing, 2021
- Modality-transfer generative adversarial network and dual-level unified latent representation for visible thermal Person re-identificationThe Visual Computer, 2020
- Dynamic Dual-Attentive Aggregation Learning for Visible-Infrared Person Re-identification2020
- Pose-Normalized Image Generation for Person Re-identification2018
- Pose Transferrable Person Re-identification2018
- Non-local Neural Networks2018
- Realtime Multi-person 2D Pose Estimation Using Part Affinity Fields2017