An Investigation of the Domain Gap in CLIP-Based Person Re-Identification
Sensors · 09.01.2025 · 25 (2) · 363
DOI: 10.3390/s25020363 ↗Kurz gefasst
Fachartikel in der Zeitschrift Sensors, online erschienen am 09.01.2025. Verfasst von Andrea Asperti und 2 weiteren Autor:innen. Beteiligte Einrichtung: Department of Informatics-Science and Engineering (DISI), University of Bologna, 40126 Bologna, Italy. Die Arbeit wurde bisher 12-mal zitiert (Crossref) und nennt 53 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Future AI Research (FAIR), National Recovery and Resilience Plan (NRRP), European Union—NextGenerationEU.
Abstract (Originalsprache)
Person re-identification (re-id) is a critical computer vision task aimed at identifying individuals across multiple non-overlapping cameras, with wide-ranging applications in intelligent surveillance systems. Despite recent advances, the domain gap—performance degradation when models encounter unseen datasets—remains a critical challenge. CLIP-based models, leveraging multimodal pre-training, offer potential for mitigating this issue by aligning visual and textual representations. In this study, we provide a comprehensive quantitative analysis of the domain gap in CLIP-based re-id systems across standard benchmarks, including Market-1501, DukeMTMC-reID, MSMT17, and Airport, simulating real-world deployment conditions. We systematically measure the performance of these models in terms of mean average precision (mAP) and Rank-1 accuracy, offering insights into the challenges faced during dataset transitions. Our analysis highlights the specific advantages introduced by CLIP’s visual–textual alignment and evaluates its contribution relative to strong image encoder baselines. Additionally, we evaluate the impact of extending training sets with non-domain-specific data and incorporating random erasing augmentation, achieving an average improvement of +4.3% in mAP and +4.0% in Rank-1 accuracy. Our findings underscore the importance of standardized benchmarks and systematic evaluations for enhancing reproducibility and guiding future research. This work contributes to a deeper understanding of the domain gap in re-id, while highlighting pathways for improving model robustness and generalization in diverse, real-world scenarios.
Schlagwörter
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Department of Informatics-Science and Engineering (DISI), University of Bologna, 40126 Bologna, Italy.
ORCID-Profile: Andrea Asperti, Salvatore Fiorilla
Förderung
- Future AI Research (FAIR)
- National Recovery and Resilience Plan (NRRP)
- European Union—NextGenerationEU
Zitieren
APA
Asperti, A., Naldi, L., & Fiorilla, S. (2025). An Investigation of the Domain Gap in CLIP-Based Person Re-Identification. Sensors, 25(2), 363. https://doi.org/10.3390/s25020363
Vancouver
Asperti A, Naldi L, Fiorilla S. An Investigation of the Domain Gap in CLIP-Based Person Re-Identification. Sensors. 2025;25(2):363. doi:10.3390/s25020363
BibTeX
@article{Asperti2025,
author = {Asperti, Andrea and Naldi, Leonardo and Fiorilla, Salvatore},
title = {An Investigation of the Domain Gap in CLIP-Based Person Re-Identification},
journal = {Sensors},
year = {2025},
volume = {25},
number = {2},
pages = {363},
doi = {10.3390/s25020363}
}
EUVIMED