no code implementations • 9 Jan 2024 • Yufei Guo, Yuanpei Chen
However, training an SNN directly poses a challenge due to the undefined gradient of the firing spike process.
1 code implementation • 11 Dec 2023 • Yufei Guo, Yuanpei Chen, Xiaode Liu, Weihang Peng, Yuhan Zhang, Xuhui Huang, Zhe Ma
To handle the problem, we propose a ternary spike neuron to transmit information.
1 code implementation • NeurIPS 2023 • Dayong Ren, Zhe Ma, Yuanpei Chen, Weihang Peng, Xiaode Liu, Yuhan Zhang, Yufei Guo
We discover that the two huge obstacles limiting the application of SNNs in point clouds are: the intrinsic optimization obstacle of SNNs that impedes the training of a big spiking model with large time steps, and the expensive memory and computation cost of PointNet that makes training a big spiking point model unrealistic.
no code implementations • 11 Sep 2023 • Binghao Huang, Yuanpei Chen, Tianyu Wang, Yuzhe Qin, Yaodong Yang, Nikolay Atanasov, Xiaolong Wang
Humans throw and catch objects all the time.
no code implementations • 2 Sep 2023 • Yuanpei Chen, Chen Wang, Li Fei-Fei, C. Karen Liu
However, the challenges arise due to the high-dimensional action space of dexterous hand and complex compositional dynamics of the long-horizon tasks.
1 code implementation • ICCV 2023 • Yufei Guo, Yuhan Zhang, Yuanpei Chen, Weihang Peng, Xiaode Liu, Liwen Zhang, Xuhui Huang, Zhe Ma
All these BNs are suggested to be used after the convolution layer as usually doing in CNNs.
2 code implementations • ICCV 2023 • Yufei Guo, Xiaode Liu, Yuanpei Chen, Liwen Zhang, Weihang Peng, Yuhan Zhang, Xuhui Huang, Zhe Ma
Spiking Neural Networks (SNNs) as one of the biology-inspired models have received much attention recently.
no code implementations • 10 Jul 2023 • Yufei Guo, Yuanpei Chen, Liwen Zhang, Xiaode Liu, Xinyi Tong, Yuanyuan Ou, Xuhui Huang, Zhe Ma
The Spiking Neural Network (SNN) has attracted more and more attention recently.
1 code implementation • 21 Jun 2023 • Yufei Guo, Yuanpei Chen, Zhe Ma
However, the neuromorphic data consists of asynchronous event spikes, which makes it difficult to construct a big benchmark to train a power general neural network model, thus limiting the neuromorphic data understanding for ``unseen" objects by deep learning.
no code implementations • 3 May 2023 • Yufei Guo, Weihang Peng, Yuanpei Chen, Liwen Zhang, Xiaode Liu, Xuhui Huang, Zhe Ma
In this paper, we propose a joint training framework of ANN and SNN, in which the ANN can guide the SNN's optimization.
no code implementations • 10 Apr 2023 • Zihan Ding, Yuanpei Chen, Allen Z. Ren, Shixiang Shane Gu, Qianxu Wang, Hao Dong, Chi Jin
Generating human-like behavior on robots is a great challenge especially in dexterous manipulation tasks with robotic hands.
1 code implementation • CVPR 2023 • Qi Ming, Lingjuan Miao, Zhe Ma, Lin Zhao, Zhiqiang Zhou, Xuhui Huang, Yuanpei Chen, Yufei Guo
In this paper, we propose a Gradient-Corrected IoU (GCIoU) loss to achieve fast and accurate 3D bounding box regression.
2 code implementations • CVPR 2023 • Liwen Zhang, Xinyan Zhang, Youcheng Zhang, Yufei Guo, Yuanpei Chen, Xuhui Huang, Zhe Ma
However, neither the regular convolution operation nor the modified ones are specific to interpret radar signals.
no code implementations • NeurIPS 2022 • Yufei Guo, Yuanpei Chen, Liwen Zhang, Xiaode Liu, YingLei Wang, Xuhui Huang, Zhe Ma
To deal with this problem, the Information maximization loss (IM-Loss) that aims at maximizing the information flow in the SNN is proposed in the paper.
Ranked #6 on Event data classification on CIFAR10-DVS
1 code implementation • 13 Oct 2022 • Yufei Guo, Liwen Zhang, Yuanpei Chen, Xinyi Tong, Xiaode Liu, YingLei Wang, Xuhui Huang, Zhe Ma
Motivated by this assumption, a training-inference decoupling method for SNNs named as Real Spike is proposed, which not only enjoys both unshared convolution kernels and binary spikes in inference-time but also maintains both shared convolution kernels and Real-valued Spikes during training.
1 code implementation • 26 Sep 2022 • Yiran Geng, Boshi An, Haoran Geng, Yuanpei Chen, Yaodong Yang, Hao Dong
Such contact prediction process then leads to an end-to-end affordance learning framework that can generalize over different types of manipulation tasks.
1 code implementation • 17 Jun 2022 • Yuanpei Chen, Tianhao Wu, Shengjie Wang, Xidong Feng, Jiechuang Jiang, Stephen Marcus McAleer, Yiran Geng, Hao Dong, Zongqing Lu, Song-Chun Zhu, Yaodong Yang
In this study, we propose the Bimanual Dexterous Hands Benchmark (Bi-DexHands), a simulator that involves two dexterous hands with tens of bimanual manipulation tasks and thousands of target objects.
no code implementations • CVPR 2022 • Yufei Guo, Xinyi Tong, Yuanpei Chen, Liwen Zhang, Xiaode Liu, Zhe Ma, Xuhui Huang
Unfortunately, with the propagation of binary spikes, the distribution of membrane potential will shift, leading to degeneration, saturation, and gradient mismatch problems, which would be disadvantageous to the network optimization and convergence.