A Hybrid SNN-ANN Network for Event-based Object Detection with Spatial and Temporal Attention

arXiv:2403.10173v1 Announce Type: new
Abstract: Event cameras offer high temporal resolution and dynamic range with minimal motion blur, making them promising for object detection tasks. While Spiking Neural Networks (SNNs) are a natural match for event-based sensory data and enable ultra-energy efficient and low latency inference on neuromorphic hardware, Artificial Neural Networks (ANNs) tend to display more stable training dynamics and faster convergence resulting in greater task performance. Hybrid SNN-ANN approaches are a promising alternative, enabling to leverage the strengths …

abstract ann arxiv attention cameras cs.ai cs.cv data detection dynamic energy energy efficient event hybrid inference latency low low latency making match natural network networks neural networks object sensory snn spatial spiking neural networks tasks temporal them type