1 code implementation • 25 Oct 2023 • Wei Fang, Yanqi Chen, Jianhao Ding, Zhaofei Yu, Timothée Masquelier, Ding Chen, Liwei Huang, Huihui Zhou, Guoqi Li, Yonghong Tian
Spiking neural networks (SNNs) aim to realize brain-inspired intelligence on neuromorphic chips with high energy efficiency by introducing neural dynamics and spike properties.
1 code implementation • ICCV 2023 • Man Yao, Jiakui Hu, Guangshe Zhao, Yaoyuan Wang, Ziyang Zhang, Bo Xu, Guoqi Li
In this work, we pose and focus on three key questions regarding the inherent redundancy in SNNs.
1 code implementation • 12 Aug 2023 • Xuerui Qiu, Rui-Jie Zhu, Yuhong Chou, Zhaorui Wang, Liang-Jian Deng, Guoqi Li
Experiments on CIFAR10/100 and ImageNet datasets demonstrate that GAC achieves state-of-the-art accuracy with remarkable efficiency.
Ranked #4 on Image Classification on CIFAR-10 (Accuracy metric)
1 code implementation • ICCV 2023 • Qiaoyi Su, Yuhong Chou, Yifan Hu, Jianing Li, Shijie Mei, Ziyang Zhang, Guoqi Li
Spiking neural networks (SNNs) are brain-inspired energy-efficient models that encode information in spatiotemporal dynamics.
1 code implementation • NeurIPS 2023 • Man Yao, Jiakui Hu, Zhaokun Zhou, Li Yuan, Yonghong Tian, Bo Xu, Guoqi Li
In this paper, we incorporate the spike-driven paradigm into Transformer by the proposed Spike-driven Transformer with four unique properties: 1) Event-driven, no calculation is triggered when the input of Transformer is zero; 2) Binary spike communication, all matrix multiplications associated with the spike matrix can be transformed into sparse additions; 3) Self-attention with linear complexity at both token and channel dimensions; 4) The operations between spike-form Query, Key, and Value are mask and addition.
no code implementations • 9 Jun 2023 • Yang Tian, Zeren Tan, Hedong Hou, Guoqi Li, Aohua Cheng, Yike Qiu, Kangyu Weng, Chun Chen, Pei Sun
These problems stem from the non-triviality and immaturity of the physical theories that analytically derive brain criticality and the statistic techniques that estimate brain criticality from empirical data.
no code implementations • 8 Jun 2023 • Gongshu Wang, Ning Jiang, Yunxiao Ma, Tiantian Liu, Duanduan Chen, Jinglong Wu, Guoqi Li, Dong Liang, Tianyi Yan
In this work, we propose a connectional style contextual representation learning model (CS-CRL) to capture the intrinsic pattern of the brain, used for multiple brain disease diagnosis.
no code implementations • 20 May 2023 • Man Yao, Yuhong Chou, Guangshe Zhao, Xiawu Zheng, Yonghong Tian, Bo Xu, Guoqi Li
LTH opens up a new path for network pruning.
no code implementations • 10 Mar 2023 • Xiang Li, Guoqi Li, Leitao Gao, Beibei Li, Gaoxi Xiao
In this paper, we propose to study on sufficient control of complex networks which is to control a sufficiently large portion of the network, where only the quantity of controllable nodes matters.
1 code implementation • 27 Feb 2023 • Rui-Jie Zhu, Qihang Zhao, Guoqi Li, Jason K. Eshraghian
As a result, their performance lags behind modern deep learning, and we are yet to see the effectiveness of SNNs in language generation.
2 code implementations • 27 Jan 2023 • Guangyao Chen, Peixi Peng, Guoqi Li, Yonghong Tian
The accumulation in AAP could compensate for the information loss during the forward and backward of full spike propagation, and facilitate the training of the FSNN.
no code implementations • 22 Nov 2022 • Xiaoshan Wu, Weihua He, Man Yao, Ziyang Zhang, Yaoyuan Wang, Guoqi Li
Spiking neural network is a novel event-based computational paradigm that is considered to be well suited for processing event camera tasks.
2 code implementations • 17 Nov 2022 • Xiao Wang, Zongzhen Wu, Bo Jiang, Zhimin Bao, Lin Zhu, Guoqi Li, YaoWei Wang, Yonghong Tian
The main streams of human activity recognition (HAR) algorithms are developed based on RGB cameras which are suffered from illumination, fast motion, privacy-preserving, and large energy consumption.
no code implementations • 28 Sep 2022 • Man Yao, Guangshe Zhao, Hengyu Zhang, Yifan Hu, Lei Deng, Yonghong Tian, Bo Xu, Guoqi Li
On ImageNet-1K, we achieve top-1 accuracy of 75. 92% and 77. 08% on single/4-step Res-SNN-104, which are state-of-the-art results in SNNs.
no code implementations • 13 Jul 2022 • Yang Tian, Guoqi Li, Pei Sun
The brain works as a dynamic system to process information.
1 code implementation • 8 Jul 2022 • Yu Du, Miaojing Shi, Fangyun Wei, Guoqi Li
In this paper, we propose a new framework to boost ZSL by explicitly learning attribute prototypes beyond images and contrastively optimizing them with attribute-level features within images.
1 code implementation • CVPR 2022 • Yu Du, Fangyun Wei, Zihe Zhang, Miaojing Shi, Yue Gao, Guoqi Li
In this paper, we introduce a novel method, detection prompt (DetPro), to learn continuous prompt representations for open-vocabulary object detection based on the pre-trained vision-language model.
1 code implementation • 2 Mar 2022 • Yihan Lin, Yifan Hu, Shijie Ma, Guoqi Li, Dongjie Yu
In this work, a new SNN training paradigm is proposed by combining the concepts of the two different training methods with the help of the pretrain technique and BP-based deep SNN training mechanism.
no code implementations • 10 Feb 2022 • Xin Liu, Mingyu Yan, Lei Deng, Guoqi Li, Xiaochun Ye, Dongrui Fan, Shirui Pan, Yuan Xie
Next, we provide comparisons from aspects of the efficiency and characteristics of these methods.
1 code implementation • 15 Dec 2021 • Yifan Hu, Lei Deng, Yujie Wu, Man Yao, Guoqi Li
Despite the rapid progress of neuromorphic computing, inadequate capacity and insufficient representation power of spiking neural networks (SNNs) severely restrict their application scope in practice.
no code implementations • 9 Dec 2021 • Yifan Hu, Yujie Wu, Lei Deng, Guoqi Li
In this paper, we identify the crux and then propose a novel residual block for SNNs, which is able to significantly extend the depth of directly trained SNNs, e. g., up to 482 layers on CIFAR-10 and 104 layers on ImageNet, without observing any slight degradation problem.
1 code implementation • 23 Oct 2021 • Yihan Lin, Wei Ding, Shaohua Qiang, Lei Deng, Guoqi Li
With event-driven algorithms, especially the spiking neural networks (SNNs), achieving continuous improvement in neuromorphic vision processing, a more challenging event-stream-dataset is urgently needed.
no code implementations • 30 Aug 2021 • Yang Wu, Dingheng Wang, Xiaotong Lu, Fan Yang, Guoqi Li, Weisheng Dong, Jianbo Shi
Visual recognition is currently one of the most important and active research areas in computer vision, pattern recognition, and even the general field of artificial intelligence.
no code implementations • ICCV 2021 • Man Yao, Huanhuan Gao, Guangshe Zhao, Dingheng Wang, Yihan Lin, ZhaoXu Yang, Guoqi Li
However, when aggregating individual events into frames with a new higher temporal resolution, existing SNN models do not attach importance to that the serial frames have different signal-to-noise ratios since event streams are sparse and non-uniform.
Ranked #5 on Audio Classification on SHD
no code implementations • 25 Jul 2021 • Ling Liang, Zheng Qu, Zhaodong Chen, Fengbin Tu, Yujie Wu, Lei Deng, Guoqi Li, Peng Li, Yuan Xie
Although spiking neural networks (SNNs) take benefits from the bio-plausible neural modeling, the low accuracy under the common local synaptic plasticity learning rules limits their application in many practical tasks.
no code implementations • 30 Jun 2021 • Mingkun Xu, Yujie Wu, Lei Deng, Faqiang Liu, Guoqi Li, Jing Pei
Biological spiking neurons with intrinsic dynamics underlie the powerful representation and learning capabilities of the brain for processing multimodal information in complex environments.
no code implementations • 27 May 2021 • Yukuan Yang, Xiaowei Chi, Lei Deng, Tianyi Yan, Feng Gao, Guoqi Li
In summary, the EOQ framework is specially designed for reducing the high cost of convolution and BN in network training, demonstrating a broad application prospect of online training in resource-limited devices.
no code implementations • 10 Mar 2021 • Xin Liu, Mingyu Yan, Lei Deng, Guoqi Li, Xiaochun Ye, Dongrui Fan
Graph Convolutional Networks (GCNs) have received significant attention from various research fields due to the excellent performance in learning graph representations.
no code implementations • 1 Jan 2021 • Zhaodong Chen, Zhao WeiQin, Lei Deng, Guoqi Li, Yuan Xie
Moreover, analysis on the activation's mean in the forward pass reveals that the self-normalization property gets weaker with larger fan-in of each layer, which explains the performance degradation on large benchmarks like ImageNet.
no code implementations • 30 Nov 2020 • Jiayi Yang, Lei Deng, Yukuan Yang, Yuan Xie, Guoqi Li
However, neural network quantization can be used to reduce computation load while maintaining comparable accuracy and original network structure.
no code implementations • 12 Nov 2020 • Zhenzhi Wu, Hehui Zhang, Yihan Lin, Guoqi Li, Meng Wang, Ye Tang
To address this issue, in this work, we propose a Leaky Integrate and Analog Fire (LIAF) neuron model, so that analog values can be transmitted among neurons, and a deep network termed as LIAF-Net is built on it for efficient spatiotemporal processing.
2 code implementations • 29 Oct 2020 • Hanle Zheng, Yujie Wu, Lei Deng, Yifan Hu, Guoqi Li
To this end, we propose a threshold-dependent batch normalization (tdBN) method based on the emerging spatio-temporal backpropagation, termed "STBP-tdBN", enabling direct training of a very deep SNN and the efficient implementation of its inference on neuromorphic hardware.
1 code implementation • NeurIPS 2020 • Yukuan Yang, Fangyun Wei, Miaojing Shi, Guoqi Li
In this paper, we restore the negative information in few-shot object detection by introducing a new negative- and positive-representative based metric learning framework and a new inference scheme with negative and positive representatives.
no code implementations • 21 Aug 2020 • Dingheng Wang, Bijiao Wu, Guangshe Zhao, Man Yao, Hengnu Chen, Lei Deng, Tianyi Yan, Guoqi Li
Recurrent neural networks (RNNs) are powerful in the tasks oriented to sequential data, such as natural language processing and video recognition.
no code implementations • 29 Jun 2020 • Bijiao Wu, Dingheng Wang, Guangshe Zhao, Lei Deng, Guoqi Li
We further theoretically and experimentally discover that the HT format has better performance on compressing weight matrices, while the TT format is more suited for compressing convolutional kernels.
no code implementations • 5 Jun 2020 • Yujie Wu, Rong Zhao, Jun Zhu, Feng Chen, Mingkun Xu, Guoqi Li, Sen Song, Lei Deng, Guanrui Wang, Hao Zheng, Jing Pei, Youhui Zhang, Mingguo Zhao, Luping Shi
We demonstrate the advantages of this model in multiple different tasks, including few-shot learning, continual learning, and fault-tolerance learning in neuromorphic vision sensors.
1 code implementation • 2 May 2020 • Weihua He, Yujie Wu, Lei Deng, Guoqi Li, Haoyu Wang, Yang Tian, Wei Ding, Wenhui Wang, Yuan Xie
Neuromorphic data, recording frameless spike events, have attracted considerable attention for the spatiotemporal information components and the event-driven processing fashion.
Ranked #11 on Gesture Recognition on DVS128 Gesture
no code implementations • 1 Jan 2020 • Ling Liang, Xing Hu, Lei Deng, Yujie Wu, Guoqi Li, Yufei Ding, Peng Li, Yuan Xie
Recently, backpropagation through time inspired learning algorithms are widely introduced into SNNs to improve the performance, which brings the possibility to attack the models accurately given Spatio-temporal gradient maps.
1 code implementation • 1 Jan 2020 • Zhaodong Chen, Lei Deng, Bangyan Wang, Guoqi Li, Yuan Xie
Powered by our metric and framework, we analyze extensive initialization, normalization, and network structures.
no code implementations • 28 Dec 2019 • Yukuan Yang, Lei Deng, Peng Jiao, Yansong Chua, Jing Pei, Cheng Ma, Guoqi Li
In summary, this work provides a new solution for lensless imaging through scattering media using transfer learning in DNNs.
1 code implementation • 20 Dec 2019 • Faqiang Liu, Mingkun Xu, Guoqi Li, Jing Pei, Luping Shi, Rong Zhao
Generative adversarial networks have achieved remarkable performance on various tasks but suffer from training instability.
no code implementations • 8 Dec 2019 • Dingheng Wang, Guangshe Zhao, Guoqi Li, Lei Deng, Yang Wu
However, due to the higher dimension of convolutional kernels, the space complexity of 3DCNNs is generally larger than that of traditional two dimensional convolutional neural networks (2DCNNs).
Ranked #1 on Quantization on Knowledge-based:
1 code implementation • 3 Nov 2019 • Lei Deng, Yujie Wu, Yifan Hu, Ling Liang, Guoqi Li, Xing Hu, Yufei Ding, Peng Li, Yuan Xie
As well known, the huge memory and compute costs of both artificial neural networks (ANNs) and spiking neural networks (SNNs) greatly hinder their deployment on edge devices with high efficiency.
no code implementations • 25 Sep 2019 • Faqiang Liu, Mingkun Xu, Guoqi Li, Jing Pei, Luping Shi
Generative adversarial networks have achieved remarkable performance on various tasks but suffer from sensitivity to hyper-parameters, training instability, and mode collapse.
no code implementations • 15 Sep 2019 • Zheyu Yang, Yujie Wu, Guanrui Wang, Yukuan Yang, Guoqi Li, Lei Deng, Jun Zhu, Luping Shi
To the best of our knowledge, DashNet is the first framework that can integrate and process ANNs and SNNs in a hybrid paradigm, which provides a novel solution to achieve both effectiveness and efficiency for high-speed object tracking.
2 code implementations • 5 Sep 2019 • Yukuan Yang, Shuang Wu, Lei Deng, Tianyi Yan, Yuan Xie, Guoqi Li
In this way, all the operations in the training and inference can be bit-wise operations, pushing towards faster processing speed, decreased memory cost, and higher energy efficiency.
1 code implementation • 2 Jul 2019 • Jibin Wu, Yansong Chua, Malu Zhang, Guoqi Li, Haizhou Li, Kay Chen Tan
Spiking neural networks (SNNs) represent the most prominent biologically inspired computing model for neuromorphic computing (NC) architectures.
no code implementations • ICLR 2019 • Zhaodong Chen, Lei Deng, Guoqi Li, Jiawei Sun, Xing Hu, Ling Liang, YufeiDing, Yuan Xie
We identify that the effectiveness expects less data correlation while the efficiency expects regular execution pattern.
no code implementations • 15 Feb 2019 • Jibin Wu, Yansong Chua, Malu Zhang, Qu Yang, Guoqi Li, Haizhou Li
Deep spiking neural networks (SNNs) support asynchronous event-driven computation, massive parallelism and demonstrate great potential to improve the energy efficiency of its synchronous analog counterpart.
no code implementations • NeurIPS 2018 • Peiqi Wang, Xinfeng Xie, Lei Deng, Guoqi Li, Dongsheng Wang, Yuan Xie
For example, we improve the perplexity per word (PPW) of a ternary LSTM on Penn Tree Bank (PTB) corpus from 126 (the state-of-the-art result to the best of our knowledge) to 110. 3 with a full precision model in 97. 2, and a ternary GRU from 142 to 113. 5 with a full precision model in 102. 7.
no code implementations • 25 Oct 2018 • Zhaodong Chen, Lei Deng, Guoqi Li, Jiawei Sun, Xing Hu, Xin Ma, Yuan Xie
In this paper, we propose alleviating this problem through sampling only a small fraction of data for normalization at each iteration.
no code implementations • ICLR 2019 • Liu Liu, Lei Deng, Xing Hu, Maohua Zhu, Guoqi Li, Yufei Ding, Yuan Xie
We propose to execute deep neural networks (DNNs) with dynamic and sparse graph (DSG) structure for compressive memory and accelerative execution during both training and inference.
no code implementations • 16 Sep 2018 • Yujie Wu, Lei Deng, Guoqi Li, Jun Zhu, Luping Shi
Spiking neural networks (SNNs) that enables energy efficient implementation on emerging neuromorphic hardware are gaining more attention.
no code implementations • 25 Jul 2018 • Ling Liang, Lei Deng, Yueling Zeng, Xing Hu, Yu Ji, Xin Ma, Guoqi Li, Yuan Xie
Crossbar architecture based devices have been widely adopted in neural network accelerators by taking advantage of the high efficiency on vector-matrix multiplication (VMM) operations.
no code implementations • 27 Feb 2018 • Shuang Wu, Guoqi Li, Lei Deng, Liu Liu, Yuan Xie, Luping Shi
Batch Normalization (BN) has been proven to be quite effective at accelerating and improving the training of deep neural networks (DNNs).
3 code implementations • ICLR 2018 • Shuang Wu, Guoqi Li, Feng Chen, Luping Shi
Researches on deep neural networks with discrete parameters and their deployment in embedded systems have been active and promising topics.
no code implementations • 7 Feb 2018 • Hongmin Li, Guoqi Li, Hanchao Liu, Luping Shi
Firstly, the event number of each pixel of the HR DVS image is determined with a sparse signal representation based method to obtain the HR event-count map from that of the LR DVS recording.
1 code implementation • 8 Jun 2017 • Yujie Wu, Lei Deng, Guoqi Li, Jun Zhu, Luping Shi
By simultaneously considering the layer-by-layer spatial domain (SD) and the timing-dependent temporal domain (TD) in the training phase, as well as an approximated derivative for the spike activity, we propose a spatio-temporal backpropagation (STBP) training framework without using any complicated technology.
1 code implementation • 25 May 2017 • Lei Deng, Peng Jiao, Jing Pei, Zhenzhi Wu, Guoqi Li
Through this way, we build a unified framework that subsumes the binary or ternary networks as its special cases, and under which a heuristic algorithm is provided at the website https://github. com/AcrossV/Gated-XNOR.
no code implementations • 18 Oct 2015 • Hongmin Li, Pei Jing, Guoqi Li
Neuromorphic vision is a concept defined by incorporating neuromorphic vision sensors such as silicon retinas in vision processing system.