Chinese | English

Search in the results

CASIA OpenIR

Browse/Search Results:  1-10 of 13 Help

Selected(0)Clear Items/Page:    Sort:
Pruning-aware Sparse Regularization for Network Pruning 期刊论文
Machine Intelligence Research, 2023, 卷号: 20, 期号: 1, 页码: 109-120
Authors:  Nan-Fei Jiang
Adobe PDF(1665Kb)  |  Favorite  |  View/Download：39/5  |  Submit date：2023/01/18
Deep learning  convolutional neural network (CNN)  model compression and acceleration  network pruning  regularization  
Efficient Visual Recognition: A Survey on Recent Advances and Brain-inspired Methodologies 期刊论文
Machine Intelligence Research, 2022, 卷号: 19, 期号: 5, 页码: 366-411
Authors:  Yang Wu
Adobe PDF(6780Kb)  |  Favorite  |  View/Download：34/2  |  Submit date：2022/09/30
Visual recognition  deep neural networks (DNNS)  brain-inspired methodologies  network compression  dynamic inference  survey  
Deep Neural Network Self-Distillation Exploiting Data Representation Invariance 期刊论文
IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS, 2022, 卷号: 33, 期号: 1, 页码: 257-269
Authors:  Xu, Ting-Bing;  Liu, Cheng-Lin
Favorite  |  View/Download：62/0  |  Submit date：2022/02/16
Training  Nonlinear distortion  Data models  Neural networks  Knowledge engineering  Network architecture  Generalization error  network compression  representation invariance  self-distillation (SD)  
Learning-based Tensor Decomposition with Adaptive Rank Penalty for CNNs Compression 会议论文
, Tokyo, Japan (online), September 8-10, 2021
Authors:  Deli, Yu;  Peipei, Yang;  Cheng-Lin, Liu
Adobe PDF(309Kb)  |  Favorite  |  View/Download：193/11  |  Submit date：2021/07/01
low-rank decomposition  network compression  learning-based decomposition  adaptive rank penalty  
CNQ: Compressor-Based Non-uniform Quantization of Deep Neural NetworksInspec keywordsOther keywordsKey words 期刊论文
CHINESE JOURNAL OF ELECTRONICS, 2020, 卷号: 29, 期号: 6, 页码: 1126-1133
Authors:  Yuan, Yong;  Chen, Chen;  Hu, Xiyuan;  Peng, Silong
Favorite  |  View/Download：124/0  |  Submit date：2021/03/08
entropy  image classification  learning (artificial intelligence)  neural nets  object detection  optimisation  quantisation (signal)  network structure  DNN  low-bit quantization  time-consuming training  compressor-based fast nonuniform quantization method  quantization model  post-training quantization methods  deep neural networks  network quantization  compressor-based nonuniform quantization  CNQ  Non-uniform quantization  Knowledge distillation  Unlabeled samples  Network compression  
EvoQ: Mixed Precision Quantization of DNNs via Sensitivity Guided Evolutionary Search 会议论文
, Glasgow, United Kingdom, 19-24 July 2020
Authors:  Yong Yuan;  Chen Chen;  Xiyuan Hu;  Silong Peng
View  |  Adobe PDF(862Kb)  |  Favorite  |  View/Download：98/27  |  Submit date：2020/10/27
evolutionary algorithm, mixed precision quantization, network compression, deep learning  
Dynamical Channel Pruning by Conditional Accuracy Change for Deep Neural Networks 期刊论文
IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS, 2020, 卷号: 无, 期号: 无, 页码: 无
Authors:  Chen, Zhiqiang;  Xu, Ting-Bing;  Du, Changde;  Liu, Cheng-Lin;  He, Huiguang
View  |  Adobe PDF(4352Kb)  |  Favorite  |  View/Download：119/13  |  Submit date：2021/01/27
Conditional accuracy change (CAC), direct criterion, dynamical channel pruning, neural network compression, structure shaping.  
CNQ:Compressor-Based Non-uniform Quantization of Deep Neural Networks 期刊论文
Chinese Journal of Electronics, 2020, 卷号: 29, 期号: 6, 页码: 1126-1133
Authors:  Yuan Yong;  Chen Chen;  Hu Xiyuan;  Peng Silong
Favorite  |  View/Download：101/0  |  Submit date：2021/03/15
Non-uniform quantization  Knowledge distillation  Unlabeled samples  Network compression  
无权访问的条目 期刊论文
Authors:  Xu, Ting-Bing;  Yang, Peipei;  Zhang, Xu-Yao;  Liu, Cheng-Lin
Adobe PDF(1571Kb)  |  Favorite  |  View/Download：33/11  |  Submit date：2019/07/12
Quantized CNN: A Unified Approach to Accelerate and Compress Convolutional Networks 期刊论文
IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS, 2018, 卷号: 29, 期号: 10, 页码: 4730-4743
Authors:  Cheng, Jian;  Wu, Jiaxiang;  Leng, Cong;  Wang, Yuhang;  Hu, Qinghao
Favorite  |  View/Download：181/0  |  Submit date：2019/12/16
Acceleration And Compression  Convolutional Neural Network (Cnn)  Mobile Devices  Product Quantization