Lightweight Person Re-Identification for Edge Computing

In person re-identification, most prevalent models are predominantly designed for cloud computing environments which introduces complexities that limit their effectiveness in edge computing scenarios. Person re-identification systems optimized for edge computing can achieve real-time or near-real-ti...

Full description

Saved in:
Bibliographic Details
Published in:IEEE access 2024, Vol.12, p.75899-75906
Main Authors: Jin, Wang, Yanbin, Dong, Haiming, Chen
Format: Article
Language:English
Subjects:
Accuracy
Cloud computing
Computational modeling
Dimensional attention mechanism
Distillation
Edge computing
Feature extraction
Identification of persons
Inference
Knowledge engineering
Lightweight
lightweight network
Network latency
Parameter identification
Pedestrians
person re-identification
Real time
Regularization
self-distillation
System effectiveness
Tensors
Weight reduction
Citations: Items that this one cites
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:In person re-identification, most prevalent models are predominantly designed for cloud computing environments which introduces complexities that limit their effectiveness in edge computing scenarios. Person re-identification systems optimized for edge computing can achieve real-time or near-real-time responses, providing substantial practical value. Addressing this gap, this paper presents the Attention Knowledge-aided Distillation Lightweight Network (ADLN), a network architecture expressly crafted for edge computing. The ADLN enhances inference speed while maintaining accuracy, which is essential for real-time applications. The core innovation of the ADLN lies in its dimension interaction attention mechanism, strategically integrated into the network to boost recognition performance. This mechanism is complemented by a self-distillation approach, transferring attention knowledge from deeper to shallower layers, thereby streamlining the network and accelerating inference. Moreover, the ADLN employs an optimization strategy combining cross-entropy loss, weighted triplet loss regularization, and center loss, effectively reducing intra-class variances. Tested on Market1501 and DukeMTMC-ReID datasets, experiments indicate that the ADLN significantly reduces the model's parameter count and identification latency, while largely maintaining accuracy.
ISSN:2169-3536
2169-3536
DOI:10.1109/ACCESS.2024.3405169