Fully Spiking Neural Networks for Unified Frame-Event Object Tracking

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Yang, Jingjun, Fan, Liangwei, Zhang, Jinpu, Lian, Xiangkai, Shen, Hui, Hu, Dewen
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866914081166852096
author Yang, Jingjun
Fan, Liangwei
Zhang, Jinpu
Lian, Xiangkai
Shen, Hui
Hu, Dewen
author_facet Yang, Jingjun
Fan, Liangwei
Zhang, Jinpu
Lian, Xiangkai
Shen, Hui
Hu, Dewen
contents The integration of image and event streams offers a promising approach for achieving robust visual object tracking in complex environments. However, current fusion methods achieve high performance at the cost of significant computational overhead and struggle to efficiently extract the sparse, asynchronous information from event streams, failing to leverage the energy-efficient advantages of event-driven spiking paradigms. To address this challenge, we propose the first fully Spiking Frame-Event Tracking framework called SpikeFET. This network achieves synergistic integration of convolutional local feature extraction and Transformer-based global modeling within the spiking paradigm, effectively fusing frame and event data. To overcome the degradation of translation invariance caused by convolutional padding, we introduce a Random Patchwork Module (RPM) that eliminates positional bias through randomized spatial reorganization and learnable type encoding while preserving residual structures. Furthermore, we propose a Spatial-Temporal Regularization (STR) strategy that overcomes similarity metric degradation from asymmetric features by enforcing spatio-temporal consistency among temporal template features in latent space. Extensive experiments across multiple benchmarks demonstrate that the proposed framework achieves superior tracking accuracy over existing methods while significantly reducing power consumption, attaining an optimal balance between performance and efficiency.
format Preprint
id arxiv_https___arxiv_org_abs_2505_20834
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Fully Spiking Neural Networks for Unified Frame-Event Object Tracking
Yang, Jingjun
Fan, Liangwei
Zhang, Jinpu
Lian, Xiangkai
Shen, Hui
Hu, Dewen
Computer Vision and Pattern Recognition
Neural and Evolutionary Computing
The integration of image and event streams offers a promising approach for achieving robust visual object tracking in complex environments. However, current fusion methods achieve high performance at the cost of significant computational overhead and struggle to efficiently extract the sparse, asynchronous information from event streams, failing to leverage the energy-efficient advantages of event-driven spiking paradigms. To address this challenge, we propose the first fully Spiking Frame-Event Tracking framework called SpikeFET. This network achieves synergistic integration of convolutional local feature extraction and Transformer-based global modeling within the spiking paradigm, effectively fusing frame and event data. To overcome the degradation of translation invariance caused by convolutional padding, we introduce a Random Patchwork Module (RPM) that eliminates positional bias through randomized spatial reorganization and learnable type encoding while preserving residual structures. Furthermore, we propose a Spatial-Temporal Regularization (STR) strategy that overcomes similarity metric degradation from asymmetric features by enforcing spatio-temporal consistency among temporal template features in latent space. Extensive experiments across multiple benchmarks demonstrate that the proposed framework achieves superior tracking accuracy over existing methods while significantly reducing power consumption, attaining an optimal balance between performance and efficiency.
title Fully Spiking Neural Networks for Unified Frame-Event Object Tracking
topic Computer Vision and Pattern Recognition
Neural and Evolutionary Computing
url https://arxiv.org/abs/2505.20834