检索结果-内蒙古大学图书馆

2020 International Conference on High Performance Big Data and intelligent Systems, HPBD and IS 2020

作者： Lu, Yaxuan Li, Weijun Ning, Xin Dong, Xiaoli Zhang, Yakun Sun, Linjun Institute of Semiconductors Chinese Academy of Sciences Beijing100083 China Beijing Key Laboratory of Semiconductor Neural Network Intelligent Sensing and Computing Technology Beijing100083 China School of Microelectronics University of Chinese Academy of Sciences Beijing100049 China Cognitive Computing Technology Joint Laboratory Wave Group Beijing100083 China

ISBN: (纸本)9781728165110

Image quality assessment is an important and necessary task in the field of image processing. It can simulate human visual perception accurately and effectively to ensure the credibility of information. Although the existing IQA algorithm based on CNN has achieved excellent success, the generalization and robustness of the algorithm are limited due to the loss of image information during feature extraction. The research shows that the phase and amplitude of image frequency domain will change with the quality, so we proposes an image quality assessment algorithm based on dual domains fusion (DualD-IQA). Using the frequency domain and spatial domain as multiple inputs of convolutional neural network, we can complement each other to represent image quality related information. Moreover, the input of any scale can be accepted by adding bilinear pooling, so as to ensure the reliability and robustness of the quality evaluation results. Experimental results show that the algorithm in this paper achieves higher consistency and accuracy in two commonly used public databases, and has higher robustness in different distortion types and cross databases. © 2020 IEEE.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Multi-Angle Head Pose Classification when Wearing the Mask for Face Recognition under the COVID-19 Coronavirus Epidemic

Multi-Angle Head Pose Classification when Wearing the Mask f...

引用

2020 International Conference on High Performance Big Data and intelligent Systems, HPBD and IS 2020

作者： Li, Shuang Ning, Xin Yu, Lina Zhang, Liping Dong, Xiaoli Shi, Yuan He, Wei Institute of Semiconductors Chinese Academy of Sciences Beijing100083 China Beijing Key Laboratory of Semiconductor Neural Network Intelligent Sensing and Computing Technology Beijing100083 China School of Microelectronics University of Chinese Academy of Sciences Beijing100049 China Cognitive Computing Technology Joint Laboratory Wave Group Beijing100083 China

ISBN: (纸本)9781728165110

Head pose classification is widely used for the preprocessing before face recognition and multi-Angle problems, because algorithms such as face recognition often require the input image to be a front face. But affected by the COVID-19 pandemic, people wear face masks to protect themselves safe, which makes cover most areas of the face. This makes some common algorithms cannot be applied to head pose classification in the new situation. Therefore, this paper established a method HGL to deal with the head pose classification by adopting color texture analysis of images and line portrait. The proposed HGL method combines the H-channel of the HSV color space with the face portrait and grayscale image, and train the CNN to extract features for classification. The evaluation on MAFA dataset shows that compared with the algorithms based on facial landmark detection and convolutional neural network, the proposed method has achieved a better performance (Front accuracy: 93.64%, Side accuracy: 87.17%). © 2020 IEEE.

关键词： Face recognition

来源：评论

学校读者我要写书评

暂无评论

Conditional generative adversarial networks based on the principle of homologycontinuity for face aging

Conditional generative adversarial networks based on the pri...

引用

作者： Ning, Xin Gou, Duoduo Dong, Xiaoli Tian, Weijuan Yu, Lina Wang, Chuansheng Institute of Semiconductors Chinese Academy of Sciences Beijing China Cognitive Computing Technology Joint Laboratory Wave Group Beijing China School of Microelectronics University of Chinese Academy of Sciences Beijing China Beijing Key Laboratory of Semiconductor Neural Network Intelligent Sensing and Computing Technology Beijing China Shenzhen Institutes of Advanced Technology Chinese Academy of Science Shen Zhen China

Age is one of the most important biological characteristics of the human face. The increase of age coincides with the increase of the aging degree of the face. Face aging synthesis is attracting increasingly more attention from domestic and overseas scholars in the computer vision and computer graphics fields, and it can be integrated into the basic research of face correlation, such as cross-age face analysis and age estimation. At present, some achievements have been made in face aging synthesis research;however, it is still an urgent problem to reduce the number of parameters and computational complexity of the network while ensuring the aging effect. Therefore, a new face aging algorithm is proposed in this article. Unlike the previous methods of aging process simulation, we introduce an assisted age classification network based on the principle of homology continuity, which is more in line with the human cognition process. After pretraining, the result of age classification is improved, and the pretraining model is then added to the framework of aging face generation for fine-tuning to constrain the generated aging face, which can improve the aging accuracy of the generated image. Furthermore, we reconstruct the input face by using the age tag of the input face and the synthesized aging face and maintain the identity invariance in the face aging process by minimizing the reconstruction loss. The experimental results show that the method proposed in this article produces a considerable effect of face aging and significantly reduces the number of parameters and the complexity of computational. © 2020 John Wiley & Sons, Ltd.

关键词： Generative adversarial networks

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

Blind separation of noncooperative paired carrier multiple access signals based on improved quantum-inspired evolutionary algorithm and receding horizon optimization

Blind separation of noncooperative paired carrier multiple a...

引用

作者： Deng, Qi Zhang, Shanshan Chen, Gang Lu, Huaxiang Lab of Artificial Networks Institute of Semiconductors CAS Beijing China University of Chinese Academy of Sciences Beijing China CAS Center for Excellence in Brain Science and Intelligence Technology Chinese Academy of Sciences Beijing China Beijing Key Laboratory of Semiconductor Neural Network Intelligent Sensing and Computing Technology Beijing China

The single-channel blind source separation of paired carrier multiple access (PCMA) signal is a key technology in satellite communications. Due to the high-order complexity of existing separation methods and the uncertainty of channel parameters, the processing of noncooperative PCMA signals with long memory remains a great challenge. In this article, the blind separation was solved as the joint channel estimation and sequence detection, and a novel blind separation algorithm based on the improved quantum-inspired evolutionary algorithm (IQEA) and receding horizon optimization was proposed. Considering the practical scenarios, a mixed PCMA signal model with noninteger period sampling was presented in advance. Combined with the proposed signal model, the IQEA was applied to recover the uplink signals from the mixed PCMA signals by its iterative estimation. Meanwhile, to reduce the computational complexity caused by long memory of PCMA signals, the receding horizon optimization was introduced to process the whole signal sequence as a dynamic programming problem. The simulation results verified that the proposed RH-IQEA outperforms existing state-of-the-art separation algorithms in the blind separation of noncooperative PCMA signals, with higher accuracy, lower-order complexity and stronger robustness to parameter estimation errors. © 2021 John Wiley & Sons, Ltd.

关键词： Iterative methods

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

A hardware-friendly low-bit post-training quantization algorithm for lightweight networks

TechRxiv

引用

TechRxiv 2023年

作者： Li, Jixing Zhao, Zhiyuan Chen, Gang Jin, Ming Lu, Huaxiang Institute of Semiconductors Chinese Academy of Sciences Beijing100083 China University of Chinese Academy of Sciences Beijing100089 China Beijing Key Lab of Semiconductor Neural Network Intelligent Perception and Computing Technology Beijing100083 China

Lightweight convolutional neural networks (LCNNs) are commonly quantized and deployed on edge devices to fulfill the requirements of low-power, high-performance tasks. Utilizing uniform, symmetric, per-tensor quantization with power-of-two scale factors can enhance hardware efficiency, albeit at the cost of significant accuracy degradation. In this work, we present a hardware-friendly post-training quantization (HFPTQ) framework to address this problem. HFPTQ employs a synergistic combination of established techniques, including Cross-Layer Equalization (CLE), Absorbing High Bias (AHB), and Adaptive Rounding. Furthermore, HFPTQ introduces quantization-aware equalization by optimizing the equalization scale and absorption vector to minimize block reconstruction error and network prediction difference. Additionally, HFPTQ introduces an adaptive bias correction mechanism. While optimizing weight rounding, bias term is co-optimized to rectify the mean shift in activations induced by quantization. Experimental results, based on the ImageNet dataset, demonstrate that HFPTQ significantly enhances the low-bit hardware-friendly quantization performance of lightweight networks. © 2023, CC BY.

关键词： Image enhancement

来源：评论

学校读者我要写书评

暂无评论

TRANSFORMER-BASED MODEL FOR SYMBOLIC REGRESSION VIA JOINT SUPERVISED LEARNING 11

TRANSFORMER-BASED MODEL FOR SYMBOLIC REGRESSION VIA JOINT SU...

引用

11th International Conference on Learning Representations, ICLR 2023

作者： Li, Wenqiang Li, Weijun Sun, Linjun Wu, Min Yu, Lina Liu, Jingyi Li, Yanjie Tian, Songsong Institute of Semiconductors Chinese Academy of Sciences Beijing China School of Electronic Electrical and Communication Engineering University of Chinese Academy of Sciences Beijing China School of Integrated Circuits University of Chinese Academy of Sciences Beijing China Beijing Key Laboratory of Semiconductor Neural Network Intelligent Sensing and Computing Technology Beijing China

Symbolic regression (SR) is an important technique for discovering hidden mathematical expressions from observed ***-based approaches have been widely used for machine translation due to their high performance, and are recently highly expected to be used for *** input the data points, then output the expression skeleton, and finally optimize the ***, recent transformer-based methods for SR focus more attention on large scale training data and ignore the ill-posed problem: the lack of sufficient supervision, i.e., expressions that may be completely different have the same supervision because of their same skeleton, which makes it challenging to deal with data that may be from the same expression skeleton but with different ***, we present a transformer-based model for SR with the ability to alleviate this ***, we leverage a feature extractor based on pure residual MLP networks to obtain more information about data ***, the core idea is that we propose a joint learning mechanism combining supervised contrastive learning, which makes features of data points from expressions with the same skeleton more similar so as to effectively alleviates the ill-posed *** benchmark results show that the proposed method is up to 25% higher with respect to the recovery rate of skeletons than typical transformer-based ***, our method outperforms state-of-the-art SR methods based on reinforcement learning and genetic programming in terms of the coefficient of determination (R2). © 2023 11th International Conference on Learning Representations, ICLR 2023. All rights reserved.

关键词： Genetic programming

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：