5 papers
SPEAR: Structured Pruning for Spiking Neural Networks via Synaptic Operation Estimation and Reinforcement Learning
Hui Xie, Yuhe Liu, Shaoqi Yang +6
While deep spiking neural networks (SNNs) demonstrate superior performance, their deployment on resource-constrained neuromorphic hardware still remains challenging. Network prunin…
ReverB-SNN: Reversing Bit of the Weight and Activation for Spiking Neural Networks
Yufei Guo, Yuhan Zhang, Zhou Jie +5
The Spiking Neural Network (SNN), a biologically inspired neural network infrastructure, has garnered significant attention recently. SNNs utilize binary spike activations for effi…
Spiking Transformer:Introducing Accurate Addition-Only Spiking Self-Attention for Transformer
Yufei Guo, Xiaode Liu, Yuanpei Chen +3
Transformers have demonstrated outstanding performance across a wide range of tasks, owing to their self-attention mechanism, but they are highly energy-consuming. Spiking Neural N…
Improving Transformer Based Line Segment Detection with Matched Predicting and Re-ranking
Xin Tong, Shi Peng, Baojie Tian +3
Classical Transformer-based line segment detection methods have delivered impressive results. However, we observe that some accurately detected line segments are assigned low confi…
Take A Shortcut Back: Mitigating the Gradient Vanishing for Training Spiking Neural Networks
Yufei Guo, Yuanpei Chen, Zecheng Hao +5
The Spiking Neural Network (SNN) is a biologically inspired neural network infrastructure that has recently garnered significant attention. It utilizes binary spike activations to…