no code implementations • 14 Mar 2023 • Haibo Shen, Juyu Xiao, Yihao Luo, Xiang Cao, Liangqi Zhang, Tianjiang Wang
However, the unconventional visual signals of these cameras pose a great challenge to the robustness of spiking neural networks.
no code implementations • 24 Feb 2023 • Liangqi Zhang, Yihao Luo, Xiang Cao, Haibo Shen, Tianjiang Wang
Convolutional neural networks (CNNs) have achieved superior performance but still lack clarity about the nature and properties of feature extraction.
no code implementations • 24 Jul 2022 • Haibo Shen, Yihao Luo, Xiang Cao, Liangqi Zhang, Juyu Xiao, Tianjiang Wang
Consistent with the ALTP phenomenon, the AIA neuron model is adaptive to input stimuli, and internal associative learning occurs only when both dendrites are stimulated at the same time.
no code implementations • 24 Jul 2022 • Haibo Shen, Yihao Luo, Xiang Cao, Liangqi Zhang, Juyu Xiao, Tianjiang Wang
Neuromorphic vision sensors (event cameras) are inherently suitable for spiking neural networks (SNNs) and provide novel neuromorphic vision data for this biomimetic model.
1 code implementation • 21 Jul 2022 • Liangqi Zhang, Haibo Shen, Yihao Luo, Xiang Cao, Leixilan Pan, Tianjiang Wang, Qi Feng
Our VGNetG-1. 0MP achieves 67. 7% top-1 accuracy with 0. 99M parameters and 69. 2% top-1 accuracy with 1. 14M parameters on ImageNet classification dataset.
no code implementations • 9 Aug 2021 • Yihao Luo, Xiang Cao, Juntao Zhang, Peng Cheng, Tianjiang Wang, Qi Feng
With the continuous improvement of the performance of object detectors via advanced model architectures, imbalance problems in the training process have received more attention.
1 code implementation • 19 Mar 2021 • Yihao Luo, Juntao Zhang, Xiang Cao, Jingjuan Guo, Haibo Shen, Tianjiang Wang, Qi Feng
Instead of the original 1x1 convolution and linear upsampling, it mitigates the information loss due to channel reduction.
no code implementations • 17 Mar 2020 • Yihao Luo, Min Xu, Caihong Yuan, Xiang Cao, Liangqi Zhang, Yan Xu, Tianjiang Wang, Qi Feng
Recently spiking neural networks (SNNs), the third-generation of neural networks has shown remarkable capabilities of energy-efficient computing, which is a promising alternative for deep neural networks (DNNs) with high energy consumption.