Showing cs.CVShow all
2 papers · 1 filter
cs.CV2025
CSDformer: A Conversion Method for Fully Spike-Driven Transformer
Yuhao Zhang, Chengjun Zhang, Di Wu +2
Spike-based transformer is a novel architecture aiming to enhance the performance of spiking neural networks while mitigating the energy overhead inherent to transformers. However,…
cs.CV2025
Ultra-Low-Latency Spiking Neural Networks with Temporal-Dependent Integrate-and-Fire Neuron Model for Objects Detection
Chengjun Zhang, Yuhao Zhang, Jie Yang +1
Spiking Neural Networks (SNNs), inspired by the brain, are characterized by minimal power consumption and swift inference capabilities on neuromorphic hardware, and have been widel…