Multi-attention-based soft partition network for vehicle re-identification
Journal of Computational Design and Engineering · 10.03.2023 · 10 (2) · 488-502
DOI: 10.1093/jcde/qwad014 ↗Kurz gefasst
Fachartikel in der Zeitschrift Journal of Computational Design and Engineering, online erschienen am 23.02.2023. Verfasst von Sangrok Lee und 2 weiteren Autor:innen. Die Arbeit wurde bisher 21-mal zitiert (Crossref) und nennt 63 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: NRF, Korean Ministry of Education, Science and Technology.
Abstract (Originalsprache)
Vehicle re-identification helps in distinguishing between images of the same and other vehicles. It is a challenging process because of significant intra-instance differences between identical vehicles from different views and subtle inter-instance differences between similar vehicles. To solve this issue, researchers have extracted view-aware or part-specific features via spatial attention mechanisms, which usually result in noisy attention maps or otherwise require expensive additional annotation for metadata, such as key points, to improve the quality. Meanwhile, based on the researchers’ insights, various handcrafted multi-attention architectures for specific viewpoints or vehicle parts have been proposed. However, this approach does not guarantee that the number and nature of attention branches will be optimal for real-world re-identification tasks. To address these problems, we proposed a new vehicle re-identification network based on a multiple soft attention mechanism for capturing various discriminative regions from different viewpoints more efficiently. Furthermore, this model can significantly reduce the noise in spatial attention maps by devising a new method for creating an attention map for insignificant regions and then excluding it from generating the final result. We also combined a channel-wise attention mechanism with a spatial attention mechanism for the efficient selection of important semantic attributes for vehicle re-identification. Our experiments showed that our proposed model achieved a state-of-the-art performance among the attention-based methods without metadata and was comparable to the approaches using metadata for the VehicleID and VERI-Wild datasets.
Förderung
- NRF
- Korean Ministry of Education, Science and Technology
Zitieren
APA
Lee, S., Woo, T., & Lee, S. H. (2023). Multi-attention-based soft partition network for vehicle re-identification. Journal of Computational Design and Engineering, 10(2), 488-502. https://doi.org/10.1093/jcde/qwad014
Vancouver
Lee S, Woo T, Lee SH. Multi-attention-based soft partition network for vehicle re-identification. Journal of Computational Design and Engineering. 2023;10(2):488-502. doi:10.1093/jcde/qwad014
BibTeX
@article{Lee2023,
author = {Lee, Sangrok and Woo, Taekang and Lee, Sang Hun},
title = {Multi-attention-based soft partition network for vehicle re-identification},
journal = {Journal of Computational Design and Engineering},
year = {2023},
volume = {10},
number = {2},
pages = {488--502},
doi = {10.1093/jcde/qwad014}
}
EUVIMED