cs.NENov 17, 2026

EM-SDTrack: Efficient Multi-Scale Spike-driven Tracking for Event Cameras

Authors: Yimeng Shan, Haodi Wu, Wei Zheng, Xiaowei Ye, Shuai Wang, Yu Liang, Wei Hua, Chenxiao Dou, 

Organizations: University of Electronic Science and Technology of China, China · Shenzhen Loop Area Institute, China · China Nanhu Academy of Electronics and Information Technology, China

Abstract

Event-driven spiking neural networks (SNNs) match the sparse spatiotemporal output of event cameras, making spike-driven trackers highly attractive for neuromorphic edge deployment. However, events reveal a target only through their spatial distribution, whose extent varies more than tenfold within one sequence. Event tracking therefore demands multi-scale representation, which existing spike-driven trackers lack. Transferring multi-scale schemes from artificial neural networks either breaks spike-driven inference with floating-point multiplication or repeats backbone computation across input scales. To address this, we propose Spike-driven Multi-Scale Interaction (SDMI), which performs cross-scale interaction in a single spiking forward pass. Its core, Dyadic Spike Sampling (DSS), restricts sampling coordinates to dyadic fractions and thus requires only shifts and additions. The resulting M-SDTrack is fully spike-driven at inference. For tighter edge budgets, we further propose Polarity-Privileged Distillation (PPD), which distils M-SDTrack into EM-SDTrack. PPD treats the event counts cancelled by the voxel representation as privileged information. Its core constraint, Polarity-Guided Curvature Distillation (PGCD), aligns the curvature of the template-search relation under polarity-guided perturbations. On FE108, FELT and VisEvent, M-SDTrack achieves state-of-the-art accuracy with an AUC of 65.1, 41.7 and 42.0. EM-SDTrack retains 99% of the accuracy of its teacher M-SDTrack-Tiny with 27% of its energy and 18% of its parameters. On the Lynxi KA200 neuromorphic chip, it runs losslessly in real time at 116 FPS and 0.12 W.

Figures & tables

Explore similar work

CardsList
  1. SpikeTrack: A Spike-driven Framework for Efficient Visual Tracking

    Feb 27, 2026Qiuyang Zhang, Jiujun Cheng, Qichao Mao +5Visual Object TrackingSpiking Neural Networks

  2. Bullet Trains: Parallelizing Training of Temporally Precise Spiking Neural Networks

    Feb 27, 2026Todd Morrill, Christian Pehle, Anthony ZadorSpiking Neural NetworksNeuromorphic Computing

  3. Sequence-SOD: Bio-inspired Sequence-aware Spiking ObjectDetection for Event Cameras

    Jul 29, 2026Katharina Bendig, René Schuster, Didier StrickerSpiking Neural NetworksEvent-Based Object Detection