Efficient Spike-driven Transformer for High-performance Drone-View Geo-Localization

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Chen, Zhongwei, Rong, Hai-Jun, Yang, Zhao-Xu, Li, Guoqi
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866915760327098368
author Chen, Zhongwei
Rong, Hai-Jun
Yang, Zhao-Xu
Li, Guoqi
author_facet Chen, Zhongwei
Rong, Hai-Jun
Yang, Zhao-Xu
Li, Guoqi
contents Traditional drone-view geo-localization (DVGL) methods based on artificial neural networks (ANNs) have achieved remarkable performance. However, ANNs rely on dense computation, which results in high power consumption. In contrast, spiking neural networks (SNNs), which benefit from spike-driven computation, inherently provide low power consumption. Regrettably, the potential of SNNs for DVGL has yet to be thoroughly investigated. Meanwhile, the inherent sparsity of spike-driven computation for representation learning scenarios also results in loss of critical information and difficulties in learning long-range dependencies when aligning heterogeneous visual data sources. To address these, we propose SpikeViMFormer, the first SNN framework designed for DVGL. In this framework, a lightweight spike-driven transformer backbone is adopted to extract coarse-grained features. To mitigate the loss of critical information, the spike-driven selective attention (SSA) block is designed, which uses a spike-driven gating mechanism to achieve selective feature enhancement and highlight discriminative regions. Furthermore, a spike-driven hybrid state space (SHS) block is introduced to learn long-range dependencies using a hybrid state space. Moreover, only the backbone is utilized during the inference stage to reduce computational cost. To ensure backbone effectiveness, a novel hierarchical re-ranking alignment learning (HRAL) strategy is proposed. It refines features via neighborhood re-ranking and maintains cross-batch consistency to directly optimize the backbone. Experimental results demonstrate that SpikeViMFormer outperforms state-of-the-art SNNs. Compared with advanced ANNs, it also achieves competitive performance.Our code is available at https://github.com/ISChenawei/SpikeViMFormer
format Preprint
id arxiv_https___arxiv_org_abs_2512_19365
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Efficient Spike-driven Transformer for High-performance Drone-View Geo-Localization
Chen, Zhongwei
Rong, Hai-Jun
Yang, Zhao-Xu
Li, Guoqi
Computer Vision and Pattern Recognition
Traditional drone-view geo-localization (DVGL) methods based on artificial neural networks (ANNs) have achieved remarkable performance. However, ANNs rely on dense computation, which results in high power consumption. In contrast, spiking neural networks (SNNs), which benefit from spike-driven computation, inherently provide low power consumption. Regrettably, the potential of SNNs for DVGL has yet to be thoroughly investigated. Meanwhile, the inherent sparsity of spike-driven computation for representation learning scenarios also results in loss of critical information and difficulties in learning long-range dependencies when aligning heterogeneous visual data sources. To address these, we propose SpikeViMFormer, the first SNN framework designed for DVGL. In this framework, a lightweight spike-driven transformer backbone is adopted to extract coarse-grained features. To mitigate the loss of critical information, the spike-driven selective attention (SSA) block is designed, which uses a spike-driven gating mechanism to achieve selective feature enhancement and highlight discriminative regions. Furthermore, a spike-driven hybrid state space (SHS) block is introduced to learn long-range dependencies using a hybrid state space. Moreover, only the backbone is utilized during the inference stage to reduce computational cost. To ensure backbone effectiveness, a novel hierarchical re-ranking alignment learning (HRAL) strategy is proposed. It refines features via neighborhood re-ranking and maintains cross-batch consistency to directly optimize the backbone. Experimental results demonstrate that SpikeViMFormer outperforms state-of-the-art SNNs. Compared with advanced ANNs, it also achieves competitive performance.Our code is available at https://github.com/ISChenawei/SpikeViMFormer
title Efficient Spike-driven Transformer for High-performance Drone-View Geo-Localization
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2512.19365