Saved in:
Bibliographic Details
Main Authors: Zhang, Qiuyang, Cheng, Jiujun, Mao, Qichao, Liu, Cong, Fang, Yu, Li, Yuhong, Ge, Mengying, Gao, Shangce
Format: Preprint
Published: 2026
Subjects:
Online Access:https://arxiv.org/abs/2602.23963
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866910035218530304
author Zhang, Qiuyang
Cheng, Jiujun
Mao, Qichao
Liu, Cong
Fang, Yu
Li, Yuhong
Ge, Mengying
Gao, Shangce
author_facet Zhang, Qiuyang
Cheng, Jiujun
Mao, Qichao
Liu, Cong
Fang, Yu
Li, Yuhong
Ge, Mengying
Gao, Shangce
contents Spiking Neural Networks (SNNs) promise energy-efficient vision, but applying them to RGB visual tracking remains difficult: Existing SNN tracking frameworks either do not fully align with spike-driven computation or do not fully leverage neurons' spatiotemporal dynamics, leading to a trade-off between efficiency and accuracy. To address this, we introduce SpikeTrack, a spike-driven framework for energy-efficient RGB object tracking. SpikeTrack employs a novel asymmetric design that uses asymmetric timestep expansion and unidirectional information flow, harnessing spatiotemporal dynamics while cutting computation. To ensure effective unidirectional information transfer between branches, we design a memory-retrieval module inspired by neural inference mechanisms. This module recurrently queries a compact memory initialized by the template to retrieve target cues and sharpen target perception over time. Extensive experiments demonstrate that SpikeTrack achieves the state-of-the-art among SNN-based trackers and remains competitive with advanced ANN trackers. Notably, it surpasses TransT on LaSOT dataset while consuming only 1/26 of its energy. To our knowledge, SpikeTrack is the first spike-driven framework to make RGB tracking both accurate and energy efficient. The code and models are available at https://github.com/faicaiwawa/SpikeTrack.
format Preprint
id arxiv_https___arxiv_org_abs_2602_23963
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle SpikeTrack: A Spike-driven Framework for Efficient Visual Tracking
Zhang, Qiuyang
Cheng, Jiujun
Mao, Qichao
Liu, Cong
Fang, Yu
Li, Yuhong
Ge, Mengying
Gao, Shangce
Computer Vision and Pattern Recognition
Spiking Neural Networks (SNNs) promise energy-efficient vision, but applying them to RGB visual tracking remains difficult: Existing SNN tracking frameworks either do not fully align with spike-driven computation or do not fully leverage neurons' spatiotemporal dynamics, leading to a trade-off between efficiency and accuracy. To address this, we introduce SpikeTrack, a spike-driven framework for energy-efficient RGB object tracking. SpikeTrack employs a novel asymmetric design that uses asymmetric timestep expansion and unidirectional information flow, harnessing spatiotemporal dynamics while cutting computation. To ensure effective unidirectional information transfer between branches, we design a memory-retrieval module inspired by neural inference mechanisms. This module recurrently queries a compact memory initialized by the template to retrieve target cues and sharpen target perception over time. Extensive experiments demonstrate that SpikeTrack achieves the state-of-the-art among SNN-based trackers and remains competitive with advanced ANN trackers. Notably, it surpasses TransT on LaSOT dataset while consuming only 1/26 of its energy. To our knowledge, SpikeTrack is the first spike-driven framework to make RGB tracking both accurate and energy efficient. The code and models are available at https://github.com/faicaiwawa/SpikeTrack.
title SpikeTrack: A Spike-driven Framework for Efficient Visual Tracking
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2602.23963