检索结果-内蒙古大学图书馆

arXiv 2022年

作者： Lin, Haiyang Yan, Mingyu Wang, Duo Zou, Mo Tu, Fengbin Ye, Xiaochun Fan, Dongrui Xie, Yuan State Key Laboratory of Computer Architecture Institute of Computing Technology Chinese Academy of Sciences Beijing China University of Chinese Academy of Sciences Beijing China University of California at Santa Barbara CA United States

Previous graph analytics accelerators have achieved great improvement on throughput by alleviating irregular off-chip memory accesses. However, on-chip side datapath conflicts and design centralization have become the critical issues hindering further throughput improvement. In this paper, a general solution, Multiple-stage Decentralized Propagation network (MDP-network), is proposed to address these issues, inspired by the key idea of trading latency for throughput. Besides, a novel High throughput Graph analytics accelerator, HiGraph, is proposed by deploying MDP-network to address each issue in practice. The experiment shows that compared with state-of-the-art accelerator, HiGraph achieves up to 2.2× speedup (1.5× on average) as well as better scalability. Copyright © 2022, The Authors. All rights reserved.

关键词： Acceleration

来源：评论

学校读者我要写书评

暂无评论

Energy-efficient NTT Design with One-bank SRAM and 2-D PE Array

Energy-efficient NTT Design with One-bank SRAM and 2-D PE Ar...

引用

Design, Automation and Test in Europe Conference and Exhibition

作者： Jianan Mu Huajie Tan Jiawen Wu Haotian Lu Chip-Hong Chang Shuai Chen Shengwen Liang Jing Ye Huawei Li Xiaowei Li State Key Laboratory of Computer Architecture Institute of Computing Technology Chinese Academy of Sciences University of Chinese Academy of Sciences CASTEST Tianjin University Nanyang Technological University Rock-Solid Security Lab Fiberhome

In Number Theoretic Transform (NTT) operation, more than half of the active energy consumption stems from memory accesses. Here, we propose a generalized design method to improve the energy efficiency of NTT operation by considering the effect of processing element (PE) geometry and memory organization on the data flow between PEs and memory. To decrease the number of data bits that are required to be accessed from the memory, a two-dimensional (2-D) PE array architecture is used. A pair of ping-pong buffers are proposed to transposed swap the coefficients to enable a single bank of memory to be used with the 2-D PE array to reduce the average memory bit access energy without compromising the throughput. Our experimental results show that this design method can produce NTT accelerators with up to 69.8% saving in average energy consumption compared with the existing designs based on multi-bank SRAM and one-bank SRAM with one-dimensional PE array with the same number of PEs and total memory size.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Background subtraction on depth videos with convolutional neural networks

arXiv

引用

arXiv 2019年

作者： Wang, Xueying Liu, Lei Li, Guangli Dong, Xiao Zhao, Peng Feng, Xiaobing State Key Laboratory of Computer Architecture Institute of Computing Technology Chinese Academy of Sciences Beijing100190 China School of Computer and Control Engineering University of Chinese Academy of Sciences Beijing100049 China College of Computer Science and Technology Jilin University ChangchunJilin130012 China

Background subtraction is a significant component of computer vision systems. It is widely used in video surveillance, object tracking, anomaly detection, etc. A new data source for background subtraction appeared as the emergence of low-cost depth sensors like Microsoft Kinect, Asus Xtion PRO, etc. In this paper, we propose a background subtraction approach on depth videos, which is based on convolutional neural networks (CNNs), called BGSNet-D (BackGround Subtraction neural Networks for Depth video). The method can be used in color unavailable scenarios like poor lighting situations, and can also be applied to combine with existing RGB background subtraction methods. A preprocessing strategy is designed to reduce the influences incurred by noise from depth sensors. The experimental results on the SBM-RGBD dataset show that the proposed method outperforms existing methods on depth data, and even reaches the performance of the methods that use RGB-D data. Copyright © 2019, The Authors. All rights reserved.

关键词： Anomaly detection

来源：评论

学校读者我要写书评

暂无评论

StyleGene: Crossover and Mutation of Region-level Facial Genes for Kinship Face Synthesis

StyleGene: Crossover and Mutation of Region-level Facial Gen...

引用

Conference on computer Vision and Pattern Recognition (CVPR)

作者： Hao Li Xianxu Hou Zepeng Huang Linlin Shen Computer Vision Institute College of Computer Science and Software Engineering Shenzhen University National Engineering Laboratory for Big Data System Computing Technology Shenzhen University School of AI and Advanced Computing Xi'an Jiaotong-Liverpool University Shenzhen Institute of Artificial Intelligence and Robotics for Society Guangdong Key Laboratory of Intelligent Information Processing Shenzhen University

High-fidelity kinship face synthesis has many potential applications, such as kinship verification, missing child identification, and social media analysis. However, it is challenging to synthesize high-quality descendant faces with genetic relations due to the lack of large-scale, high-quality annotated kinship data. This paper proposes RFG (Region-level Facial Gene) extraction framework to address this issue. We propose to use IGE (Image-based Gene Encoder), LGE (Latent-based Gene Encoder) and Gene Decoder to learn the RFGs of a given face image, and the relationships between RFGs and the latent space of Style-GAN2. As cycle-like losses are designed to measure the $\mathcal{L}_{2}$ distances between the output of Gene Decoder and image encoder, and that between the output of LGE and IGE, only face images are required to train our framework, i.e. no paired kinship face data is required. Based upon the proposed RFGs, a crossover and mutation module is further designed to inherit the facial parts of parents. A Gene Pool has also been used to introduce the variations into the mutation of RFGs. The diversity of the faces of descendants can thus be significantly increased. Qualitative, quantitative, and subjective experiments on FIW, TSKinFace, and FF-Databases clearly show that the quality and diversity of kinship faces generated by our approach are much better than the existing state-of-the-art methods.

关键词：

来源：评论

学校读者我要写书评

暂无评论

GM-DF: Generalized Multi-Scenario Deepfake Detection

arXiv

引用

arXiv 2024年

作者： Lai, Yingxin Yu, Zitong Yang, Jing Li, Bin Kang, Xiangui Shen, Linlin The School of Computing and Information Technology Great Bay University Dongguan523000 China National Engineering Laboratory for Big Data System Computing Technology Shenzhen University Shenzhen518060 China Shenzhen Institute of Artificial Intelligence and Robotics for Society Shenzhen University Shenzhen518060 China The Guangdong Key Laboratory of Information Security The School of Computer Science and Engineering Sun Yat-sen University Guangzhou510080 China Computer Vision Institute School of Computer Science & Software Engineering Shenzhen Institute of Artificial Intelligence and Robotics for Society Guangdong Key Laboratory of Intelligent Information Processing National Engineering Laboratory for Big Data System Computing Technology Shenzhen University Shenzhen518060 China

Existing face forgery detection usually follows the paradigm of training models in a single domain, which leads to limited generalization capacity when unseen scenarios and unknown attacks occur. In this paper, we elaborately investigate the generalization capacity of deepfake detection models when jointly trained on multiple face forgery detection datasets. We first find a rapid degradation of detection accuracy when models are directly trained on combined datasets due to the discrepancy across collection scenarios and generation methods. To address the above issue, a Generalized Multi-Scenario Deepfake Detection framework (GM-DF) is proposed to serve multiple real-world scenarios by a unified model. First, we propose a hybrid expert modeling approach for domain-specific real/forgery feature extraction. Besides, as for the commonality representation, we use CLIP to extract the common features for better aligning visual and textual features across domains. Meanwhile, we introduce a masked image reconstruction mechanism to force models to capture rich forged details. Finally, we supervise the models via a domain-aware meta-learning strategy to further enhance their generalization capacities. Specifically, we design a novel domain alignment loss to strongly align the distributions of the meta-test domains and meta-train domains. Thus, the updated models are able to represent both specific and common real/forgery features across multiple datasets. In consideration of the lack of study of multi-dataset training, we establish a new benchmark leveraging multi-source data to fairly evaluate the models' generalization capacity on unseen scenarios. Both qualitative and quantitative experiments on five datasets conducted on traditional protocols as well as the proposed benchmark demonstrate the effectiveness of our approach. The codes will be available on https://***/laiyingxin2/GM-DF. Copyright © 2024, The Authors. All rights reserved.

关键词： Image reconstruction

来源：评论

学校读者我要写书评

暂无评论

Pinpointing the Memory Behaviors of DNN Training

Pinpointing the Memory Behaviors of DNN Training

引用

IEEE International Symposium on Performance Analysis of systems and Software

作者： Jiansong Li Xiao Dong Guangli Li Peng Zhao Xueying Wang Xiaobing Chen Xianzhi Yu Yongxin Yang Zihan Jiang Wei Cao Lei Liu Xiaobing Feng University of Chinese Academy of Sciences Beijing China Youtu Lab Tencent Shanghai China Huawei Technology Co. Ltd Beijing China State Key Laboratory of Computer Architecture Institute of Computing Technology CAS Beijing China

The training of deep neural networks (DNNs) is usually memory-hungry due to the limited device memory capacity of DNN accelerators. Characterizing the memory behaviors of DNN training is critical to optimize the device memory pressures. In this work, we pinpoint the memory behaviors of each device memory block of GPU during training by instrumenting the memory allocators of the runtime system. Our results show that the memory access patterns of device memory blocks are stable and follow an iterative fashion. These observations are useful for the future optimization of memory-efficient training from the perspective of raw memory access patterns.

关键词： Training Runtime Instruments Neural networks Graphics processing units Software Performance analysis

来源：评论

学校读者我要写书评

暂无评论

Pinpointing the memory behaviors of DNN training

arXiv

引用

arXiv 2021年

作者： Li, Jiansong Dong, Xiao Li, Guangli Zhao, Peng Wang, Xueying Chen, Xiaobing Yu, Xianzhi Yang, Yongxin Jiang, Zihan Cao, Wei Liu, Lei Feng, Xiaobing State Key Laboratory of Computer Architecture Institute of Computing Technology CAS Beijing China University of Chinese Academy of Sciences Beijing China Youtu Lab Tencent Shanghai China Huawei Technology Co. Ltd Beijing China

关键词： Deep neural networks

来源：评论

学校读者我要写书评

暂无评论

Latency-aware Partial Task Offloading in Collaborative Edge computing

Latency-aware Partial Task Offloading in Collaborative Edge ...

引用

International Conference on computer Supported Cooperative Work in Design

作者： Yingmeng Gao Jie Zhu Haiping Huang Chen Chen Nanjing University of Posts & Telecommunications Nanjing China State Key Laboratory Chinese of Computer Architecture Institute of Computing Technology Academy of Sciences Beijing China Jiangsu High Technology Reasearch Key Laboratory of Wireless Sensor Networks Nanjing China Nanjing University of Aeronautics and Astronautics Nanjing China

When it comes to the fifth generation, collaborative edge computing is preferred for offloading computation-intensive tasks of low-latency applications in Internet of Things. In this paper, we consider the partial task offloading problem where tasks can be divided into subtasks and offloaded to nearby devices. The flow scheduling problem is integrated in the offloading process, i.e., multiple and conflicting route paths are considered. We propose the latency-aware partial task offloading framework (LaPTOF) for the considered problem. LaPTOF integrates a weighted priority ranking strategy (WPRS) which generates multiple solutions with different weights on task arrival time and the task processing time. A feasible solution generation method (FSGM) is designed where the best offloaded proportion of tasks are computed, and the appropriate offloaded devices and offload paths are determined. The proposed LaPTOF has an advantage in providing a scheduling plan that minimizes total completion time of task offloading in a shorter duration. The experimental results show that the proposal is suitable for the considered problem compared with JPOFH and its variants on both effectiveness and efficiency.

关键词：

来源：评论

学校读者我要写书评

暂无评论

BuildEnVR: An Immersive Analysis system for Environmental Field

BuildEnVR: An Immersive Analysis System for Environmental Fi...

引用

International Conference on Parallel and Distributed systems (ICPADS)

作者： Zhenghan Zhou Kebin Liu Yantong Xie Hangxu Jin Shi Liu Ruiqing Wang Haitian Zhao Borong Lin Xiaofang Mu Hui Qi Global Innovation Exchange Tsinghua University Fuzhou Fuyao Institute for Advanced Study School of Architecture Carnegie Mellon University School of Architecture Tsinghua University College of Computer Science and Technology Taiyuan Normal University Shanxi Key Laboratory of Intelligent Optimization Computing and Blockchain Technology

ISBN: (数字)9798331515966

ISBN: (纸本)9798331515973

Amidst global warming and escalating extreme weather events, indoor environmental quality’s impact on human health and public hygiene gains prominence. Environmental parameters exist essentially as fields, which are characterized by high dimensionality, density and complexity, and contain massive amounts of information in space. To facilitate visualization and analysis of indoor environmental field, we design and implement BuildEnVR, an immersive analysis system by virtual reality, enabling remote analysis of real-time and historical environmental field data. Grounded in user needs and cognitive psychology, three visualization modes emerge: the Virtual Sensor mode enables users to access perceptual data in real-time at any 3D coordinates in ambient space, the 4D Heatmap mode visualizes spatial variations and trends over time in environmental field data, and the Synaesthesia mode realizes the fusion display of multi-dimensional environmental field data, allowing users to quickly understand the overall condition of the indoor environment with a low cognitive load. Extensive user surveys validate BuildEnVR’s intuitiveness and precision, and it is suitable for both experts and general users.

关键词： Wireless communication Wireless sensor networks Three-dimensional displays Buildings Psychology Data visualization Cognitive load Real-time systems Space heating Meteorology Climate change Global warming Environmental factors Immersive learning

来源：评论

学校读者我要写书评

暂无评论

Understanding the Runtime Overheads of Deep Learning Inference on Edge Devices

Understanding the Runtime Overheads of Deep Learning Inferen...

引用

IEEE International Conference on Big Data and Cloud computing (BdCloud)

作者： Xiu Ma Guangli Li Lei Liu Huaxiao Liu Xiaobing Feng College of Computer Science and Technology Jilin University China Key Laboratory of Symbolic Computation and Knowledge Engineering of Ministry of Education Jilin University China SKL of Computer Architecture Institute of Computing Technology Chinese Academy of Sciences China University of Chinese Academy of Sciences China

With the growing ubiquity of the Internet of Things, in-the-edge inference of deep neural network models has been a major driver for promoting the widespread use of intelligent applications. As model inference characteristics are crucial for optimizing and deploying deep neural networks on hardware platforms, many studies focus on analyzing the performance of neural networks such as latency, accuracy, throughput, and energy consumption. However, few existing works have ever discussed the runtime overheads hidden in neural network inference, despite the overheads are non-negligible for edge applications. The lack of in-depth analysis of the overheads hinders the understanding of how hardware designs and model structures impact on-device inference performance. In this paper, we characterize the runtime overheads of deep learning inference on representative edge devices by leveraging state-of-the-art neural network models, performing a systematical analysis from the perspective of end-to-end performance, hardware platforms, memory bandwidth, and neural network model structures. Based on experimental results, the crucial insights are offered to facilitate the design and configure of resource-efficient networks and pick appropriate models on the specific platform, which provides a comprehensive view of runtime overheads of in-the- edge neural network inference for architects and developers.

关键词： Deep learning Performance evaluation Analytical models Runtime Roads Neural networks Throughput

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：