Bio-Inspired Enhanced Quantization-Aware Training-Based Knowledge Distillation for Person Re-Identification
Biomimetics · 18.11.2026 · 11 (11) · 839
DOI: 10.3390/biomimetics11110839 ↗Kurz gefasst
Fachartikel in der Zeitschrift Biomimetics, online erschienen am 18.11.2026. Verfasst von Ho Won Lee und 5 weiteren Autor:innen. Die Arbeit nennt 59 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: National Research Foundation of Korea (NRF) grant funded by the Korea government, National Supercomputing Center at KISTI.
Abstract (Originalsprache)
Infrared (IR) person re-identification (Re-ID) supports surveillance in nighttime and low-light conditions, but low resolution, noise, and limited texture information hinder recognition. We propose a bio-inspired lightweight framework based on enhanced quantization-aware training-based knowledge distillation (EQT-KD). Selective feature suppression and adaptive weighting of head, upper-body, and lower-body regions provide a functional, design-level analogue of selective visual attention. Enhanced LightMBN serves as the teacher, while Extreme LightMBN is the compact student. EQT-KD adjusts branch-wise distillation strength according to the difference between student outputs before and after fake quantization, supporting stable knowledge transfer under quantization. Experiments on SYSU-MM01, DBPerson-Recog-DB1, and the near-infrared (NIR) subset of RGBNT201 yielded mean average precision values of 0.7646, 0.9883, and 0.7473 and Rank-1 accuracies of 0.8037, 0.9903, and 0.7547, respectively, under the IR-only protocol used in this study, in which each unseen test identity has one query and two gallery images. The student uses 2.35 million parameters and 0.66 GFLOPs. Inference-time measurements on desktop, NVIDIA Jetson Orin Nano, and mobile platforms indicate the potential for real-time processing. These results support selective feature processing and quantization-aware knowledge transfer as a practical approach to balancing recognition performance and computational efficiency in resource-constrained IR surveillance.
Förderung
- National Research Foundation of Korea (NRF) grant funded by the Korea government
- National Supercomputing Center at KISTI
Zitieren
APA
Lee, H. W., Lee, S. J., Im, S. J., Song, H. W., Jeung, I. H., & Park, K. R. (2026). Bio-Inspired Enhanced Quantization-Aware Training-Based Knowledge Distillation for Person Re-Identification. Biomimetics, 11(11), 839. https://doi.org/10.3390/biomimetics11110839
Vancouver
Lee HW, Lee SJ, Im SJ, Song HW, Jeung IH, Park KR. Bio-Inspired Enhanced Quantization-Aware Training-Based Knowledge Distillation for Person Re-Identification. Biomimetics. 2026;11(11):839. doi:10.3390/biomimetics11110839
BibTeX
@article{Lee2026,
author = {Lee, Ho Won and Lee, Sung Jae and Im, Su Jin and Song, Hyun Woo and Jeung, In Ho and Park, Kang Ryoung},
title = {Bio-Inspired Enhanced Quantization-Aware Training-Based Knowledge Distillation for Person Re-Identification},
journal = {Biomimetics},
year = {2026},
volume = {11},
number = {11},
pages = {839},
doi = {10.3390/biomimetics11110839}
}
EUVIMED