Search Results for author: Guoqi Li

Found 37 papers, 9 papers with code

Efficient Visual Recognition with Deep Neural Networks: A Survey on Recent Advances and New Directions

no code implementations30 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.

H2Learn: High-Efficiency Learning Accelerator for High-Accuracy Spiking Neural Networks

no code implementations25 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.

Temporal-wise Attention Spiking Neural Networks for Event Streams Classification

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.

Classification Gesture Recognition +1

Exploiting Spiking Dynamics with Spatial-temporal Feature Normalization in Graph Learning

no code implementations30 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.

Graph Attention Graph Learning +1

Towards Efficient Full 8-bit Integer DNN Online Training on Resource-limited Devices without Batch Normalization

no code implementations27 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.

Model Compression Quantization

Sampling methods for efficient training of graph convolutional networks: A survey

no code implementations10 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.

Redefining Self-Normalization Property

no code implementations1 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.

Data Augmentation

Training and Inference for Integer-Based Semantic Segmentation Network

no code implementations30 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.

Quantization Semantic Segmentation

LIAF-Net: Leaky Integrate and Analog Fire Network for Lightweight and Efficient Spatiotemporal Information Processing

no code implementations12 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.

Question Answering

Going Deeper With Directly-Trained Larger Spiking Neural Networks

1 code implementation29 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.

Restoring Negative Information in Few-Shot Object Detection

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.

Few-Shot Learning Few-Shot Object Detection +2

Kronecker CP Decomposition with Fast Multiplication for Compressing RNNs

no code implementations21 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.

Tensor Decomposition Video Recognition

Hybrid Tensor Decomposition in Neural Network Compression

no code implementations29 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.

Neural Network Compression Tensor Decomposition

Brain-inspired global-local learning incorporated with neuromorphic computing

no code implementations5 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.

Continual Learning Few-Shot Learning

Comparing SNNs and RNNs on Neuromorphic Vision Datasets: Similarities and Differences

1 code implementation2 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.

Fairness

Exploring Adversarial Attack in Spiking Neural Networks with Spike-Compatible Gradient

no code implementations1 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.

Adversarial Attack

A Comprehensive and Modularized Statistical Framework for Gradient Norm Equality in Deep Neural Networks

1 code implementation1 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.

Transfer Learning in General Lensless Imaging through Scattering Media

no code implementations28 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.

Transfer Learning

Adversarial symmetric GANs: bridging adversarial samples and adversarial networks

1 code implementation20 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.

Image Generation

Compressing 3DCNNs Based on Tensor Train Decomposition

no code implementations8 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).

Neural Network Compression

Comprehensive SNN Compression Using ADMM Optimization and Activity Regularization

no code implementations3 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.

Model Compression Quantization

DashNet: A Hybrid Artificial and Spiking Neural Network for High-speed Object Tracking

no code implementations15 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.

Object Tracking

Training High-Performance and Large-Scale Deep Neural Networks with Full 8-bit Integers

2 code implementations5 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.

Quantization

A Tandem Learning Rule for Effective Training and Rapid Inference of Deep Spiking Neural Networks

no code implementations2 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.

Event-based vision

Deep Spiking Neural Network with Spike Count based Learning Rule

no code implementations15 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.

HitNet: Hybrid Ternary Recurrent Neural Network

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.

Quantization

Batch Normalization Sampling

no code implementations25 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.

Dynamic Sparse Graph for Efficient Deep Learning

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.

Dimensionality Reduction

Direct Training for Spiking Neural Networks: Faster, Larger, Better

no code implementations16 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.

Crossbar-aware neural network pruning

no code implementations25 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.

Network Pruning

L1-Norm Batch Normalization for Efficient Training of Deep Neural Networks

no code implementations27 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).

Quantization

Training and Inference with Integers in Deep Neural Networks

2 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.

Continual Learning

Super-resolution of spatiotemporal event-stream image captured by the asynchronous temporal contrast vision sensor

no code implementations7 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.

Event-based vision Super-Resolution

Spatio-Temporal Backpropagation for Training High-performance Spiking Neural Networks

1 code implementation8 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.

Object Detection

GXNOR-Net: Training deep neural networks with ternary weights and activations without full-precision memory under a unified discretization framework

1 code implementation25 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.

Real-time Tracking Based on Neuromrophic Vision

no code implementations18 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.

Cannot find the paper you are looking for? You can Submit a new open access paper.