A hierarchical spiking transformer using Q-K attention achieves 85.65% top-1 accuracy on ImageNet-1K, the first direct-trained SNN to exceed 85%.
Toward scalable, efficient, and accurate deep spiking neural networks with backward residual connections, stochastic softmax, and hybridization
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.NE 1years
2024 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
QKFormer: Hierarchical Spiking Transformer using Q-K Attention
A hierarchical spiking transformer using Q-K attention achieves 85.65% top-1 accuracy on ImageNet-1K, the first direct-trained SNN to exceed 85%.