Attention Disturbance and Dual-Path Constraint Network for Occluded Person Re-identification
Proceedings of the AAAI Conference on Artificial Intelligence · 24.03.2024 · 38 (6) · 6198-6206
DOI: 10.1609/aaai.v38i6.28437 ↗Kurz gefasst
Fachartikel in der Zeitschrift Proceedings of the AAAI Conference on Artificial Intelligence, online erschienen am 24.03.2024. Verfasst von Jiaer Xia und 5 weiteren Autor:innen. Die Arbeit wurde bisher 21-mal zitiert (Crossref).
Abstract (Originalsprache)
Occluded person re-identification (Re-ID) aims to address the potential occlusion problem when matching occluded or holistic pedestrians from different camera views. Many methods use the background as artificial occlusion and rely on attention networks to exclude noisy interference. However, the significant discrepancy between simple background occlusion and realistic occlusion can negatively impact the generalization of the network. To address this issue, we propose a novel transformer-based Attention Disturbance and Dual-Path Constraint Network (ADP) to enhance the generalization of attention networks. Firstly, to imitate real-world obstacles, we introduce an Attention Disturbance Mask (ADM) module that generates an offensive noise, which can distract attention like a realistic occluder, as a more complex form of occlusion. Secondly, to fully exploit these complex occluded images, we develop a DualPath Constraint Module (DPC) that can obtain preferable supervision information from holistic images through dualpath interaction. With our proposed method, the network can effectively circumvent a wide variety of occlusions using the basic ViT baseline. Comprehensive experimental evaluations conducted on person re-ID benchmarks demonstrate the superiority of ADP over state-of-the-art methods.
Zitieren
APA
Xia, J., Tan, L., Dai, P., Zhao, M., Wu, Y., & Cao, L. (2024). Attention Disturbance and Dual-Path Constraint Network for Occluded Person Re-identification. Proceedings of the AAAI Conference on Artificial Intelligence, 38(6), 6198-6206. https://doi.org/10.1609/aaai.v38i6.28437
Vancouver
Xia J, Tan L, Dai P, Zhao M, Wu Y, Cao L. Attention Disturbance and Dual-Path Constraint Network for Occluded Person Re-identification. Proceedings of the AAAI Conference on Artificial Intelligence. 2024;38(6):6198-6206. doi:10.1609/aaai.v38i6.28437
BibTeX
@article{Xia2024,
author = {Xia, Jiaer and Tan, Lei and Dai, Pingyang and Zhao, Mingbo and Wu, Yongjian and Cao, Liujuan},
title = {Attention Disturbance and Dual-Path Constraint Network for Occluded Person Re-identification},
journal = {Proceedings of the AAAI Conference on Artificial Intelligence},
year = {2024},
volume = {38},
number = {6},
pages = {6198--6206},
doi = {10.1609/aaai.v38i6.28437}
}
EUVIMED