检索结果-内蒙古大学图书馆

Learning to represent 2D human face with mathematical model

CAAI Transactions on Intelligence technology 2024年第1期9卷 54-68页

作者： Liping Zhang Weijun Li Linjun Sun Lina Yu Xin Ning Xiaoli Dong AnnLab Institute of SemiconductorsChinese Academy of SciencesBeijingChina Center of Materials Science and Optoelectronics Engineering School of Integrated CircuitsUniversity of Chinese Academy of SciencesBeijingChina Beijing Key Laboratory of Semiconductor Neural Network Intelligent Sensing and Computing Technology BeijingChina

How to represent a human face pattern?While it is presented in a continuous way in human visual system,computers often store and process it in a discrete manner with 2D arrays of *** authors attempt to learn a continuous surface representation for face image with explicit ***,an explicit model(EmFace)for human face representation is pro-posed in the form of a finite sum of mathematical terms,where each term is an analytic function ***,to estimate the unknown parameters of EmFace,a novel neural network,EmNet,is designed with an encoder-decoder structure and trained from massive face images,where the encoder is defined by a deep convolutional neural network and the decoder is an explicit mathematical expression of *** authors demonstrate that our EmFace represents face image more accurate than the comparison method,with an average mean square error of 0.000888,0.000936,0.000953 on LFW,IARPA Janus Benchmark-B,and IJB-C *** results show that,EmFace has a higher representation performance on faces with various expressions,postures,and other ***,EmFace achieves reasonable performance on several face image processing tasks,including face image restoration,denoising,and transformation.

关键词： artificial neural networks face analysis image processing mathematics computing

来源：评论

学校读者我要写书评

暂无评论

Unveiling the relationship between Fabry-Perot laser structures and optical field distribution via symbolic regression

引用

Optoelectronics Letters 2025年第3期21卷 149-154页

作者： LI Wenqiang WU Min LI Weijun HAO Meilan YU Lina AnnLab Institute of SemiconductorsChinese Academy of SciencesBeijing100083China School of Electronic Electrical and Communication Engineering&School of Integrated CircuitsUniversity of Chinese Academy of SciencesBeijing100049China Beijing Key Laboratory of Semiconductor Neural Network Intelligent Sensing and Computing Technology Beijing100083China

In recent years,machine learning(ML)techniques have been shown to be effective in accelerating the development process of optoelectronic ***,as"black box"models,they have limited theoretical *** this work,we leverage symbolic regression(SR)technique for discovering the explicit symbolic relationship between the structure of the optoelectronic Fabry-Perot(FP)laser and its optical field distribution,which greatly improves model transparency compared to *** demonstrated that the expressions explored through SR exhibit lower errors on the test set compared to ML models,which suggests that the expressions have better fitting and generalization capabilities.

关键词： machine learning optoelectronic deviceshoweverasblack optical field distributionwhich symbolic regression symbolic regression sr technique Fabry Perot laser discovering explicit symbolic relationship optical field distribution

来源：评论

学校读者我要写书评

暂无评论

Mathematical representation of 2D image boundary contour using fractional implicit polynomial

引用

Optoelectronics Letters 2023年第4期19卷 252-256页

作者： TONG Yuerong YU Lina LI Weijun LIU Jingyi WU Min YANG Yafei Institute of Semiconductors Chinese Academy of SciencesBeijing 100083China School of Materials Science and Optoelectronic Technology&School of Integrated Circuits University of Chinese Academy of SciencesBeijing 100049China Beijing Key Laboratory of Semiconductor Neural Network Intelligent Sensing and Computing Technology Beijing 100083China DapuStor Corporation Shenzhen 518100China

Implicit polynomial(IP)fitting is an effective method to quickly represent two-dimensional(2D)image boundary contour in the form of mathematical *** the same maximum degree,the fractional implicit polynomial(FIP)can express more curve details than IP and has obvious advantages for the representation of complex boundary *** existing studies,algebraic distance is mainly used as the fitting objective of the *** the time cost is reduced,there are problems of low fitting accuracy and spurious zero *** this paper,we propose a two-stage neural network with differentiable geometric distance,which uses FIP to achieve mathematical representation,called *** the first stage,the continuity constraint is used to obtain a rough outline of the fitting *** the second stage,differentiable geometric distance is gradually added to fine-tune the polynomial coefficients to obtain a contour representation with higher *** results show that TSEncoder can achieve mathematical representation of 2D image boundary contour with high accuracy.

关键词： polynomial contour representation

来源：评论

学校读者我要写书评

暂无评论

Blind image quality assessment based on the multiscale and dual-domains features fusion

Blind image quality assessment based on the multiscale and d...

引用

作者： Lu, Yaxuan Li, Weijun Ning, Xin Dong, Xiaoli Zhang, Liping Sun, Linjun Cheng, Chuantong Institute of Semiconductors Chinese Academy of Sciences Beijing China Beijing Key Laboratory of Semiconductor Neural Network Intelligent Sensing and Computing Technology Beijing China School of Microelectronics University of Chinese Academy of Sciences Beijing China Cognitive Computing Technology Joint Laboratory Wave Group Beijing China

Image quality assessment is to simulate subjective human visual perception and realize image quality inference automatically. Although deep neural networks have achieved great success, the majority of them do not fully consider perception characteristics. Therefore, according to the human visual scale characteristics, we proposed an image quality assessment algorithm based on multiscale and dual domains fusion. Firstly, the original image and its phase congruency respectively input into two branches, feature pyramid and channel attention mechanism are adopted to extract multiscale features. After that, bilinear pool is used to aggregate the spatial and frequency domain characteristics of the corresponding scales, and allows arbitrary scale input to ensure that the features are extracted from the inherent quality images. Finally, the single quality score is obtained through learned weights of each scale. Comparative experiments between our approach and state-of-the-art are conducted on five public databases, the results demonstrate that the proposed algorithm is not only robust to different types and across database, but also sensitive to scale. © 2021 John Wiley & Sons, Ltd.

关键词： Image quality

来源：评论

学校读者我要写书评

暂无评论

Research on Convolution Decomposition and Hardware Acceleration based on FPGA 4

Research on Convolution Decomposition and Hardware Accelerat...

引用

4th International Conference on Computer Engineering and Application, ICCEA 2023

作者： He, Jinzhong Li, Weijun Xu, Jian Zhang, Ming Yang, Huiqu Institute of Semiconductors Chinese Academy of Sciences Beijing China University of Chinese Academy of Sciences Beijing China Beijing Key Laboratory of Semiconductor Neural Network Intelligent Sensing and Computing Technology Beijing China DapuStor Corporation Shenzhen China

ISBN: (纸本)9798350347548

Convolutional neural network (CNN) is an artificial intelligence algorithm with a wide application foundation. In recent years, to improve the computational speed of the computation-intensive CNN models, many researchers have accelerated hardware implementation on FPGA. However, the acceleration algorithms are mostly unfriendly to hardware or have poor flexibility, which leads to a decrease in computing power and an increase in data access. In this paper, we propose a convolution decomposition method in the time domain, which fully considers the behavior of convolution operation and the difference between data streams in hardware. Besides, we design a hardware acceleration architecture. The results show that this design can be compatible with convolution and full connection operations of various sizes and strides. Hardware tailoring and cascade expansion are proposed for different application scenarios. Experiments show that the computing performance per DSP is 0.39 GOP/s, which demonstrates that the hardware design has a better multiplier utilization than similar works. © 2023 IEEE.

关键词： Field programmable gate arrays (FPGA)

来源：评论

学校读者我要写书评

暂无评论

General nonlinear function neural network fitting algorithm based on CNN 3

General nonlinear function neural network fitting algorithm ...

引用

3rd International Conference on Computer Vision, Image and Deep Learning and International Conference on Computer Engineering and Applications, CVIDL and ICCEA 2022

作者： Xu, Xintao Jiang, Zhelong Chen, Gang Li, Zhigang Gong, Guoliang Lu, Huaxiang University of Science and Technology of China School of Microelectronics Hefei China Institute of Semiconductors Chinese Academy of Sciences Beijing China University of Chinese Academy of Sciences Materials and Optoelectronics Research Center Beijing China Semiconductor Neural Network Intelligent Perception and Computing Technology Beijing Key Laboratory Beijing China

ISBN: (纸本)9781665459112

This paper proposes a generic neural network fitting algorithm based on CNN for nonlinear functions that overcomes the challenges of a large number of nonlinear functions in terms of hardware deployment and computing circuit generality in diverse neural network models. The model takes advantage of the principle that functions have varying degrees of difficulty fitting in different spaces, mapping the input to high-dimensional space with 1x1 convolution, and utilizing CNN to extract features of nonlinear functions with its strong feature extraction ability in high-dimensional space. Furthermore, MaxPool and ReLU improve the ability of nonlinear fitting. When fitting Tanh, Sigmoid, and ELU activation functions with 16bit accuracy, the proposed algorithm has an average error of less than 0.0006, with a parameter size of 5.793 k. © 2022 IEEE.

关键词： Functions

来源：评论

学校读者我要写书评

暂无评论

Multi-angle head pose classification with masks based on color texture analysis and stack generalization

Multi-angle head pose classification with masks based on col...

引用

作者： Li, Shuang Dong, Xiaoli Shi, Yuan Lu, Baoli Sun, Linjun Li, Wenfa Institute of Semiconductors Chinese Academy of Sciences Beijing China Cognitive Computing Technology Joint Laboratory Wave Group Beijing China Beijing Key Laboratory of Semiconductor Neural Network Intelligent Sensing and Computing Technology Beijing China Shenzhen Wave Kingdom Co. Ltd. Shenzhen China College of Robotics Beijing Union University Beijing China

Head pose classification is an important part of the preprocessing process of face recognition, which can independently solve application problems related to multi-angle. But, due to the impact of the COVID-19 coronavirus pandemic, more and more people wear masks to protect themselves, which covering most areas of the face. This greatly affects the performance of head pose classification. Therefore, this article proposes a method to classify the head pose with wearing a mask. This method focuses on the information that is helpful for head pose classification. First, the H-channel image of the HSV color space is extracted through the conversion of the color space. Then use the line portrait to extract the contour lines of the face, and train the convolutional neural networks to extract features in combination with the grayscale image. Finally, stacked generalization technology is used to fuse the output of the three classifiers to obtain the final classification result. The results on the MAFA dataset show that compared with the current advanced algorithm, the accuracy of our method is 94.14% on the front, 86.58% on the more side, and 90.93% on the side, which has better performance. © 2021 John Wiley & Sons, Ltd.

关键词： Face recognition

来源：评论

学校读者我要写书评

暂无评论

Optimizing FPGA-based DCN Accelerator with On-Chip Dataflow Reordering and Serial-Parallel computing Array 5

Optimizing FPGA-based DCN Accelerator with On-Chip Dataflow ...

引用

5th International Conference on High Performance Big Data and intelligent Systems, HDIS 2023

作者： Zhang, Ming Xu, Jian He, Jinzhong Qin, Hong AnnLab Institute of Semiconductors Chinese Academy of Sciences Beijing100083 China Beijing Key Laboratory of Semiconductor Neural Network Intelligent Sensing and Computing Technology Beijing100083 China College of Materials Science and Opto-Electronic Technology & School of Integrated Circuits University of Chinese Academy of Sciences Beijing100049 China

ISBN: (纸本)9798350394160

Deep convolutional neural networks (DCNs) have recently experienced rapid development in the direction of lightweight and edge deployment. However, accelerators for DCNs face challenges in balancing computational and data bandwidth, leading to inefficient computation and high hardware costs. Additionally, different network structures make it challenging to design and reconfigure accelerators flexibly. To address these issues, this paper proposes a parallel-serial channel accelerator system, which resolves the low utilization of multipliers caused by small channels and inadequate bandwidth of fully connected layers. The results demonstrate that the proposed accelerator in this study maintains high computational performance and efficiency on typical DCNs. When implemented on Xilinx VCU128 at 200 MHz, the peak computational performance reaches 204.5 GOPS, with an efficiency of 0.37 GOPS/DSP and a maximum utilization rate of computing array up to 99.63%, surpassing previous works. ©2023 IEEE.

关键词： Field programmable gate arrays (FPGA)

来源：评论

学校读者我要写书评

暂无评论

Novel activation function with pixelwise modeling capacity for lightweight neural network design

Novel activation function with pixelwise modeling capacity f...

引用

作者： Liu, Yi Guo, Xiaozhou Tan, Kaijun Gong, Guoliang Lu, Huaxiang Lab of Artificial Networks Institute of Semiconductors Chinese Academy of Sciences Beijing China University of Chinese Academy of Sciences Beijing China Center for Excellence in Brain Science and Intelligence Technology Chinese Academy of Sciences Shanghai China Beijing Key Laboratory of Semiconductor Neural Network Intelligent Sensing and Computing Technology Beijing China

The development of lightweight networks makes neural networks more efficient to be widely applied to various tasks. Considering the deployment of hardware like edge devices and mobile phones, we prioritize lightweight networks. However, their accuracy has always lagged far behind SOTA networks. In this article, we present a simple yet effective activation function, called WReLU, to improve the performance of lightweight networks significantly by adding a residual spatial condition. Moreover, we use a strategy to switch activation functions after determining which convolutional layer to use. We perform experiments on ImageNet 2012 classification dataset in CPU, GPU, and edge devices. Experiments demonstrate that WReLU improves the accuracy of classification significantly. Meanwhile, our strategy balances the effect of additional parameters and multiply accumulate. Our method improves the accuracy of SqueezeNet and SqueezeNext by more than 5% without increasing extensive parameters and computation. For the lightweight network with a large number of parameters, such as MobileNet and ShuffleNet, there is also a significant improvement. Additionally, the inference speed of most lightweight networks using our WReLU strategy is almost the same as the baseline model on different platforms. Our approach not only ensures the practicability of the lightweight network but also improves its performance. © 2021 John Wiley & Sons Ltd.

关键词： Classification (of information)

来源：评论

学校读者我要写书评

暂无评论

DoctorGPT: A Large Language Model with Chinese Medical Question-Answering Capabilities 5

DoctorGPT: A Large Language Model with Chinese Medical Quest...

引用

5th International Conference on High Performance Big Data and intelligent Systems, HDIS 2023

作者： Li, Wenqiang Yu, Lina Wu, Min Liu, Jingyi Hao, Meilan Li, Yanjie AnnLab Institute of Semiconductors Chinese Academy of Sciences Beijing100083 China School of Electronic Electrical and Communication Engineering & School of Integrated Circuits University of Chinese Academy of Sciences Beijing100049 China Beijing Key Laboratory of Semiconductor Neural Network Intelligent Sensing and Computing Technology Beijing100083 China

ISBN: (纸本)9798350394160

Large Language Models (LLMs) have made incredible strides recently in understanding and reacting to user intents. However, these models typically excel in English and have not been specifically trained for medical applications, leading to suboptimal performance in responding to medical inquiries such as diagnostic queries and drug recommendations. In this paper, we propose DoctorGPT, a domain-specific large language model tailored for medical question-answering tasks. DoctorGPT leverages the open-source Baichuan2 as its foundational model, undergoes extensive pre-training on medical encyclopedic data to incorporate medical knowledge, and subsequently undergoes fine-tuning on a dataset consisting of two million medical instruction-dialogue pairs to enhance its question-answering capabilities. When compared to general-purpose large models, DoctorGPT demonstrates significant advantages in Chinese medical question-answering (Q&A) tasks. ©2023 IEEE.

关键词： Medical applications

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：