Search Results for author: Chenlin Zhou

Found 3 papers, 3 papers with code

Date Published Github Stars

QKFormer: Hierarchical Spiking Transformer using Q-K Attention

2 code implementations • 25 Mar 2024 • Chenlin Zhou, Han Zhang, Zhaokun Zhou, Liutao Yu, Liwei Huang, Xiaopeng Fan, Li Yuan, Zhengyu Ma, Huihui Zhou, Yonghong Tian

ii) We incorporate the hierarchical structure, which significantly benefits the performance of both the brain and artificial neural networks, into spiking transformers to obtain multi-scale spiking representation.

35
Paper
Code

Enhancing the Performance of Transformer-based Spiking Neural Networks by SNN-optimized Downsampling with Precise Gradient Backpropagation

1 code implementation • 10 May 2023 • Chenlin Zhou, Han Zhang, Zhaokun Zhou, Liutao Yu, Zhengyu Ma, Huihui Zhou, Xiaopeng Fan, Yonghong Tian

In this paper, we propose ConvBN-MaxPooling-LIF (CML), an SNN-optimized downsampling with precise gradient backpropagation.

32
Paper
Code

Spikingformer: Spike-driven Residual Learning for Transformer-based Spiking Neural Network

1 code implementation • 24 Apr 2023 • Chenlin Zhou, Liutao Yu, Zhaokun Zhou, Zhengyu Ma, Han Zhang, Huihui Zhou, Yonghong Tian

Based on this residual design, we develop Spikingformer, a pure transformer-based spiking neural network.

55
Paper
Code
Cannot find the paper you are looking for? You can Submit a new open access paper.
Contact us on: hello@paperswithcode.com . Papers With Code is a free resource with all data licensed under CC-BY-SA.
Terms Data policy Cookies policy