Fully Spiking Neural Networks for Unified Frame-Event Object Tracking

TL;DR

This paper introduces SpikeFET, a fully spiking neural network for unified frame-event object tracking that combines local and global features efficiently, achieving high accuracy with low power consumption.

Contribution

The paper presents the first fully spiking frame-event tracking framework integrating convolutional and Transformer modules, with novel modules for positional bias removal and spatio-temporal regularization.

Findings

Achieves superior tracking accuracy compared to existing methods.

Reduces power consumption significantly while maintaining high performance.

Demonstrates effectiveness across multiple benchmark datasets.

Abstract

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.