Diversity Feature Learning Network for Occluded Person Re-Identification
Sensors · 14.08.2026 · 26 (16) · 5160
DOI: 10.3390/s26165160 ↗Kurz gefasst
Fachartikel in der Zeitschrift Sensors, online erschienen am 14.08.2026. Verfasst von Lei Qi und 2 weiteren Autor:innen. Beteiligte Einrichtung: School of Computer Science and Technology, Xinjiang University, Urumqi 830046, China. Die Arbeit nennt 52 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Ministry of Science and Technology Project - National Key Research and Development Program, Ministry of Science and Technology Project—National Key Research and Development Program.
Abstract (Originalsprache)
Occluded person re-identification (Re-ID) is a challenging task, as non-target pedestrians or surrounding obstacles often interfere with the visual cues of the target person, making it difficult for models to effectively learn discriminative feature representations. Most existing methods focus on salient body parts via spatial partitioning or external cues; however, they are either limited in capturing diverse semantic information or tend to introduce additional network complexity. To address these issues, we propose a Diversity Feature Learning Network (DFLNet). Specifically, a Scene-Level Occlusion (SLO) strategy is designed to automatically simulate two common occlusion scenarios by modeling the relative spatial relationships between the target person and surrounding occluders in real-world scenes. Subsequently, multiple class tokens are introduced to capture diverse representations of the target identity. A Token Diversity Constraint (TDC) loss is further imposed on these class tokens to encourage the learning of discriminative and diverse feature embeddings. Finally, we design a Diversity Feature Fusion (DFF) module, which facilitates the interaction and integration of dual-branch features by modeling global feature correlations and optimizing inter-feature distribution distances. Extensive experiments on occluded, partial, and holistic Re-ID datasets demonstrate the effectiveness of the proposed DFLNet.
Schlagwörter
Stichwörter der Autor:innen
Autor:innen und Institutionen
- School of Computer Science and Technology, Xinjiang University, Urumqi 830046, China.
- Xinjiang Multimodal Intelligent Processing and Information Security Engineering Technology Research Center, Urumqi 830017, China.
ORCID-Profile: Lei Qi, Liejun Wang, Shaochen Jiang
Förderung
- Ministry of Science and Technology Project - National Key Research and Development Program
- Ministry of Science and Technology Project—National Key Research and Development Program
Zitieren
APA
Qi, L., Wang, L., & Jiang, S. (2026). Diversity Feature Learning Network for Occluded Person Re-Identification. Sensors, 26(16), 5160. https://doi.org/10.3390/s26165160
Vancouver
Qi L, Wang L, Jiang S. Diversity Feature Learning Network for Occluded Person Re-Identification. Sensors. 2026;26(16):5160. doi:10.3390/s26165160
BibTeX
@article{Qi2026,
author = {Qi, Lei and Wang, Liejun and Jiang, Shaochen},
title = {Diversity Feature Learning Network for Occluded Person Re-Identification},
journal = {Sensors},
year = {2026},
volume = {26},
number = {16},
pages = {5160},
doi = {10.3390/s26165160}
}
EUVIMED