BSViT: A Burst Spiking Vision Transformer for Expressive and Efficient Visual Representation Learning
Researchers have introduced BSViT, a novel Burst Spiking Vision Transformer designed for more efficient and expressive visual representation learning. This new architecture addresses limitations in existing Spiking Vision Transformers by enhancing information capacity through a Dual-Channel Burst Spiking Self-Attention mechanism. BSViT also incorporates a patch adjacency masking strategy to reduce computational load and improve spatial awareness, demonstrating superior performance on various vision benchmarks while maintaining energy efficiency. AI
IMPACT Introduces a new architecture for energy-efficient visual learning on neuromorphic hardware.