SpikeAtConv reports state-of-the-art 81.23% top-1 ImageNet accuracy for a directly trained spiking network, but the defining attention module is unspecified and no energy data is provided.
Bottom-up and top-down approaches for the design of neuromorphic processing systems: tradeoffs and synergies between natural and artificial intelligence
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.NE 1years
2024 1verdicts
REJECT 1representative citing papers
citing papers explorer
-
SpikeAtConv: An Integrated Spiking-Convolutional Attention Architecture for Energy-Efficient Neuromorphic Vision Processing
SpikeAtConv reports state-of-the-art 81.23% top-1 ImageNet accuracy for a directly trained spiking network, but the defining attention module is unspecified and no energy data is provided.