Task-Oriented Semantic Compression for Localization at the Network Edge

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Fang, Zhengru, Hu, Senkang, Guo, Yu, Deng, Yiqin, Fang, Yuguang
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866911494487146496
author Fang, Zhengru
Hu, Senkang
Guo, Yu
Deng, Yiqin
Fang, Yuguang
author_facet Fang, Zhengru
Hu, Senkang
Guo, Yu
Deng, Yiqin
Fang, Yuguang
contents Achieving precise visual localization in GPS-limited urban environments poses significant challenges for resource-constrained mobile platforms, particularly under strict bandwidth, memory, and processing limitations. Inspired by mammalian spatial cognition, we propose a task-oriented communication framework in which bandwidth-limited endpoints equipped with multi-camera systems extract compact multi-view features and offload localization tasks to collaborative edge servers. We introduce the Orthogonally-constrained Variational Information Bottleneck encoder (O-VIB), which incorporates automatic relevance determination (ARD) to prune non-informative features while enforcing orthogonality to minimize redundancy. This enables efficient and accurate localization with minimal transmission overhead. Extensive evaluation on a real-world urban localization dataset demonstrates that O-VIB achieves high-precision localization under stringent bandwidth budgets, outperforming existing methods across diverse communication constraints.
format Preprint
id arxiv_https___arxiv_org_abs_2504_18317
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Task-Oriented Semantic Compression for Localization at the Network Edge
Fang, Zhengru
Hu, Senkang
Guo, Yu
Deng, Yiqin
Fang, Yuguang
Computer Vision and Pattern Recognition
Networking and Internet Architecture
Achieving precise visual localization in GPS-limited urban environments poses significant challenges for resource-constrained mobile platforms, particularly under strict bandwidth, memory, and processing limitations. Inspired by mammalian spatial cognition, we propose a task-oriented communication framework in which bandwidth-limited endpoints equipped with multi-camera systems extract compact multi-view features and offload localization tasks to collaborative edge servers. We introduce the Orthogonally-constrained Variational Information Bottleneck encoder (O-VIB), which incorporates automatic relevance determination (ARD) to prune non-informative features while enforcing orthogonality to minimize redundancy. This enables efficient and accurate localization with minimal transmission overhead. Extensive evaluation on a real-world urban localization dataset demonstrates that O-VIB achieves high-precision localization under stringent bandwidth budgets, outperforming existing methods across diverse communication constraints.
title Task-Oriented Semantic Compression for Localization at the Network Edge
topic Computer Vision and Pattern Recognition
Networking and Internet Architecture
url https://arxiv.org/abs/2504.18317