BSViT introduces burst spike coding and dual-channel burst spiking self-attention in a Vision Transformer, outperforming prior spiking transformers on static and event-based vision tasks with competitive energy efficiency.
Neural networks10(9), 1659–1671 (1997)
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
verdicts
UNVERDICTED 2representative citing papers
A dual memory pathway spiking network with near-memory hardware achieves long-sequence accuracy using 40-60% fewer parameters and delivers over 4X throughput plus 5X energy efficiency gains.
citing papers explorer
-
BSViT: A Burst Spiking Vision Transformer for Expressive and Efficient Visual Representation Learning
BSViT introduces burst spike coding and dual-channel burst spiking self-attention in a Vision Transformer, outperforming prior spiking transformers on static and event-based vision tasks with competitive energy efficiency.
-
Algorithm-hardware co-design of neuromorphic networks with dual memory pathways
A dual memory pathway spiking network with near-memory hardware achieves long-sequence accuracy using 40-60% fewer parameters and delivers over 4X throughput plus 5X energy efficiency gains.