检索结果-内蒙古大学图书馆

IEEE International Conference on Systems, Man and Cybernetics

作者： Jianfeng cheng Ye Liu Jian Yin Liangdao Wang Yan Pan Artificial Intelligence Department Lizhi Inc. Beijing & Guangzhou China School of Computer Science and Engineering Sun Yat-sen University Guangzhou China Guangdong Key Laboratory of Big Data Analysis and Processing Guangzhou China School of Artificial Intelligence Sun Yat-sen University Zhuhai China

ISBN: (数字)9781665410205

ISBN: (纸本)9781665410212

With the continuous expansion of robotics and digital humans in practical applications, the demand for the auditory system is becoming deeper, usually requiring more efficient speech recognition framework capabilities to handle multiple tasks and use fewer resources. In previous audio processing frameworks, each type of audio processing task typically requires constructing a standalone deep network model for training, which results in more training data and higher training time when constructing models for multi-task audio scenarios simultaneously. The recent improvement of audio models based on transformers have brought about methods that can handle multiple audio tasks concurrently. However, recent related methods still require retraining multi-task targets with an amount of data, and achieve the general effect after training for multi-task scenarios than the simple combination of standalone methods processed separately. In order to better build a model that can handle multiple audio tasks, we propose a novel framework of distillation through pre-trained large models for enhancing event tagger with automatic speech recognizer. Through multiple rounds of experiments on several audio datasets, it has been verified that the proposed framework can achieve better results than the baseline for multitasking, and comparative results with less parameters compared to the baselines for single-task scenarios.

关键词： Training Adaptation models Analytical models Training data Speech recognition Speech enhancement Multitasking Transformers data models Robots

来源：评论

学校读者我要写书评

暂无评论

P-FedAvg: Parallelizing federated learning with theoretical guarantees 40

P-FedAvg: Parallelizing federated learning with theoretical ...

引用

40th IEEE Conference on Computer Communications, INFOCOM 2021

作者： Zhong, Zhicong Zhou, Yipeng Wu, Di Chen, Xu Chen, Min Li, Chao Sheng, Quan Z. Sun Yat-Sen University School of Computer Science and Engineering Guangzhou510006 China Guangdong Key Laboratory of Big Data Analysis and Processing Guangzhou510006 China PCL Research Center of Networks and Communications Peng Cheng Laboratory Shenzhen518000 China Department of Computing Macquarie University SydneyNSW2109 Australia School of Computer Science and Technology Huazhong University of Science and Technology Wuhan430074 China Tencent Technology Co. Ltd Shenzhen China

ISBN: (纸本)9780738112817

With the growth of participating clients, the centralized parameter server (PS) will seriously limit the scale and efficiency of Federated Learning (FL). A straightforward approach to scale up the FL system is to construct a Parallel FL (PFL) system with multiple PSes. However, it is unclear whether PFL can really achieve a faster convergence rate or not. Even if the answer is yes, it is non-trivial to design a highly efficient parameter average algorithm for a PFL system. In this paper, we propose a completely parallelizable FL algorithm called P-FedAvg under the PFL architecture. P-FedAvg extends the well-known FedAvg algorithm by allowing multiple PSes to cooperate and train a learning model together. In P-FedAvg, each PS is only responsible for a fraction of total clients, but PSes can mix model parameters in a dedicatedly designed way so that the FL model can well converge. Different from heuristic-based algorithms, P-FedAvg is with theoretical guarantees. To be rigorous, we conduct theoretical analysis on the convergence rate of P-FedAvg, and derive the optimal weights for each PS to mix parameters with its neighbors. We also examine how the overlay topology formed by PSes affects the convergence rate and robustness of a PFL system. Lastly, we perform extensive experiments with real datasets to verify our analysis and demonstrate that P-FedAvg can significantly improve convergence rates than traditional FedAvg and other competitive baselines. We believe that our work can help to lay a theoretical foundation for building more efficient PFL systems. © 2021 IEEE.

关键词： Network topology

来源：评论

学校读者我要写书评

暂无评论

Restoration of User Videos Shared on Social Media

arXiv

引用

arXiv 2022年

作者： Luo, Hongming Zhou, Fei Lam, Kin-Man Qiu, Guoping College of Electronics and Information Engineering Shenzhen University China Department of Electronic and Information Engineering The Hong Kong Polytechnic University China Peng Cheng Laboratory Shenzhen China Guangdong Key Laboratory of Intelligent Information Processing Shenzhen China Shenzhen Key Laboratory of Digital Creative Technology China Shenzhen Institute for Artificial Intelligence and Robotics for Society China Guangdong-Hong Kong Joint Laboratory for Big Data Imaging and Communication China

User videos shared on social media platforms usually suffer from degradations caused by unknown proprietary processing procedures, which means that their visual quality is poorer than that of the originals. This paper presents a new general video restoration framework for the restoration of user videos shared on social media platforms. In contrast to most deep learning-based video restoration methods that perform end-to-end mapping, where feature extraction is mostly treated as a black box, in the sense that what role a feature plays is often unknown, our new method, termed Video restOration through adapTive dEgradation Sensing (VOTES), introduces the concept of a degradation feature map (DFM) to explicitly guide the video restoration process. Specifically, for each video frame, we first adaptively estimate its DFM to extract features representing the difficulty of restoring its different regions. We then feed the DFM to a convolutional neural network (CNN) to compute hierarchical degradation features to modulate an end-to-end video restoration backbone network, such that more attention is paid explicitly to potentially more difficult to restore areas, which in turn leads to enhanced restoration performance. We will explain the design rationale of the VOTES framework and present extensive experimental results to show that the new VOTES method outperforms various state-of-the-art techniques both quantitatively and qualitatively. In addition, we contribute a large scale real-world database of user videos shared on different social media platforms. Codes and datasets are available at https://***/luohongming/***. Copyright © 2022, The Authors. All rights reserved.

关键词： Restoration

来源：评论

学校读者我要写书评

暂无评论

Aesthetically Relevant Image Captioning

arXiv

引用

arXiv 2022年

作者： Zhong, Zhipeng Zhou, Fei Qiu, Guoping College of Electronics and Information Engineering Shenzhen University China Peng Cheng National Laboratory Shenzhen China Guangdong Key Laboratory of Intelligent Information Processing Shenzhen China Shenzhen Institute for Artificial Intelligence and Robotics for Society China Guangdong-Hong Kong Joint Laboratory for Big Data Imaging and Communication Shenzhen China School of Computer Science The University of Nottingham United Kingdom

Image aesthetic quality assessment (AQA) aims to assign numerical aesthetic ratings to images whilst image aesthetic captioning (IAC) aims to generate textual descriptions of the aesthetic aspects of images. In this paper, we study image AQA and IAC together and present a new IAC method termed Aesthetically Relevant Image Captioning (ARIC). Based on the observation that most textual comments of an image are about objects and their interactions rather than aspects of aesthetics, we first introduce the concept of Aesthetic Relevance Score (ARS) of a sentence and have developed a model to automatically label a sentence with its ARS. We then use the ARS to design the ARIC model which includes an ARS weighted IAC loss function and an ARS based diverse aesthetic caption selector (DACS). We present extensive experimental results to show the soundness of the ARS concept and the effectiveness of the ARIC model by demonstrating that texts with higher ARS’s can predict the aesthetic ratings more accurately and that the new ARIC model can generate more accurate, aesthetically more relevant and more diverse image captions. Furthermore, a large new research database containing 510K images with over 5 million comments and 350K aesthetic scores, and code for implementing ARIC are available at https://***/pengZai/ARIC. © 2022, CC BY-NC-ND.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Not All Diffusion Model Activations Have Been Evaluated as Discriminative Features

arXiv

引用

arXiv 2024年

作者： Meng, Benyuan Xu, Qianqian Wang, Zitai Cao, Xiaochun Huang, Qingming Institute of Information Engineering CAS China School of Cyber Security University of Chinese Academy of Sciences China Key Lab. of Intelligent Information Processing Institute of Computing Technology CAS China Peng Cheng Laboratory China School of Cyber Science and Tech. Shenzhen Campus of Sun Yat-sen University China School of Computer Science and Tech. University of Chinese Academy of Sciences China Key Laboratory of Big Data Mining and Knowledge Management CAS China

Diffusion models are initially designed for image generation. Recent research shows that the internal signals within their backbones, named activations, can also serve as dense features for various discriminative tasks such as semantic segmentation. Given numerous activations, selecting a small yet effective subset poses a fundamental problem. To this end, the early study of this field performs a large-scale quantitative comparison of the discriminative ability of the activations. However, we find that many potential activations have not been evaluated, such as the queries and keys used to compute attention scores. Moreover, recent advancements in diffusion architectures bring many new activations, such as those within embedded ViT modules. Both combined, activation selection remains unresolved but overlooked. To tackle this issue, this paper takes a further step with a much broader range of activations evaluated. Considering the significant increase in activations, a full-scale quantitative comparison is no longer operational. Instead, we seek to understand the properties of these activations, such that the activations that are clearly inferior can be filtered out in advance via simple qualitative evaluation. After careful analysis, we discover three properties universal among diffusion models, enabling this study to go beyond specific models. On top of this, we present effective feature selection solutions for several popular diffusion models. Finally, the experiments across multiple discriminative tasks validate the superiority of our method over the SOTA competitors. Our code is available at this url. © 2024, CC BY.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

Opara: Exploiting Operator Parallelism for Expediting DNN Inference on GPUs

arXiv

引用

arXiv 2023年

作者： Chen, Aodong Xu, Fei Han, Li Dong, Yuan Chen, Li Zhou, Zhi Liu, Fangming The Shanghai Key Laboratory of Multidimensional Information Processing School of Computer Science and Technology East China Normal University 3663 N. Zhongshan Road Shanghai200062 China The School of Software Engineering East China Normal University 3663 N. Zhongshan Road Shanghai200062 China The School of Computing and Informatics University of Louisiana at Lafayette 301 East Lewis Street LafayetteLA70504 United States The Guangdong Key Laboratory of Big Data Analysis and Processing School of Computer Science and Engineering Sun Yat-sen University 132 E. Waihuan Road Guangzhou510006 China Peng Cheng Laboratory Huazhong University of Science and Technology China

GPUs have become the defacto hardware devices for accelerating Deep Neural Network (DNN) inference workloads. However, the conventional sequential execution mode of DNN operators in mainstream deep learning frameworks cannot fully utilize GPU resources, even with the operator fusion enabled, due to the increasing complexity of model structures and a greater diversity of operators. Moreover, the inadequate operator launch order in parallelized execution scenarios can lead to GPU resource wastage and unexpected performance interference among operators. In this paper, we propose Opara, a resource- and interference-aware DNN Operator parallel scheduling framework to accelerate DNN inference on GPUs. Specifically, Opara first employs CUDA Streams and CUDA Graph to parallelize the execution of multiple operators automatically. To further expedite DNN inference, Opara leverages the resource demands of operators to judiciously adjust the operator launch order on GPUs, overlapping the execution of compute-intensive and memory-intensive operators. We implement and open source a prototype of Opara based on PyTorch in a non-intrusive manner. Extensive prototype experiments with representative DNN and Transformer-based models demonstrate that Opara outperforms the default sequential CUDA Graph in PyTorch and the state-of-the-art operator parallelism systems by up to 1.68× and 1.29×, respectively, yet with acceptable runtime overhead. Copyright © 2023, The Authors. All rights reserved.

关键词： Deep neural networks

来源：评论

学校读者我要写书评

暂无评论

Semantic Feature Division Multiple Access for Digital Semantic Multiple Access Channels

引用

IEEE Transactions on Cognitive Communications and Networking 2025年

作者： Shen, Bin Ma, Shuai Chen, Rui Wu, Youlong Li, Hang Shi, Guangming Li, Shiyin Al-Dhahir, Naofal China University of Mining and Technology School of Information and Control Engineering Xuzhou221116 China Xidian University State Key Laboratory of Integrated Service Networks School of Telecommunications Engineering Shaanxi Xi'an710071 China ShanghaiTech University School of Information Science and Technology Shanghai201210 China Shenzhen Research Institute of Big Data Guangdong Shenzhen518172 China Xidian University School of Artificial Intelligence Shaanxi Xi'an710071 China Peng cheng Laboratory Shenzhen518066 China The University of Texas at Dallas Department of Electrical and Computer Engineering RichardsonTX75080 United States

To solve the multi-user semantic communication network capacity bottlenecks, this paper proposes a semantic feature domain multiple access (SFDMA) scheme. By extracting and encoding semantic features and jointly processing multi-user data, the scheme can realize the encoding and transmission of multi-user semantic information in the separated feature subspace. Based on this scheme, a semantic digital multiple access network model is proposed to perform multi-user inference tasks, and an efficient semantic encoding and decoding scheme is developed by using variational information bottleneck (VIB) theory to ensure both the orthogonality in the feature domain and the classification accuracy. Furthermore, a SFDMA model for image reconstruction is designed based on the Swin Transformer. The modified model also considers the reconstruction quality and orthogonality of semantic feature domain. In addition, we design an optimization target for multiple access to implement an adaptive power allocation method for multi-user semantic communications. Simulation results show that our proposed SFDMA scheme exhibits semantic feature domain orthogonality in different applications, and the adaptive power allocation method shows excellent performance in the classification task, and effectively guarantee the quality of service (QoS) of the semantic communications. © 2015 IEEE.

关键词： Image reconstruction

来源：评论

学校读者我要写书评

暂无评论

Heterogeneous Software Effort Estimation via Cascaded Adversarial Auto-Encoder 1

引用

21st International Conference on Parallel and Distributed Computing, Applications, and Technologies, PDCAT 2020

作者： Qi, Fumin Jing, Xiao-Yuan Zhu, Xiaoke Jia, Xiaodong cheng, Li Dong, Yichuan Fang, Ziseng Ma, Fei Feng, Shengzhong College of Computer Science and Software Engineering Shenzhen University Shenzhen China School of Computer Wuhan University Wuhan China Henan Key Laboratory of Big Data Analysis and Processing Henan University Kaifeng China National Supercomputing Center in Shenzhen Guangzhou Guangdong China School of Computer Science Qufu Normal University Rizhao China

ISBN: (数字)9783030692445

ISBN: (纸本)9783030692438

In Software Effort Estimation (SEE) practice, the data drought problem has been plaguing researchers and practitioners. Leveraging heterogeneous SEE data collected by other companies is a feasible solution to relieve the data drought problem. However, how to make full use of the heterogeneous effort data to conduct SEE, which is called as Heterogeneous Software Effort Estimation (HSEE), has not been well studied. In this paper, we propose a HSEE model, called Dynamic Heterogeneous Software Effort Estimation (i.e., DHSEE), which leverages the adversarial auto-encoder and convolutional neural network techniques. Meanwhile, we have investigated the scenario of conducting HSEE with dynamically increasing effort data. Experiments on ten public datasets indicate that our approach can significantly outperform the state-of-the-art HSEE method and other competing methods on both static and dynamic SEE scenarios. © 2021, Springer Nature Switzerland AG.

关键词： Drought

来源：评论

学校读者我要写书评

暂无评论

AdAUC: End-to-end Adversarial AUC Optimization Against Long-tail Problems

arXiv

引用

arXiv 2022年

作者： Hou, Wenzheng Xu, Qianqian Yang, Zhiyong Bao, Shilong He, Yuan Huang, Qingming Key Laboratory of Intelligent Information Processing Institute of Computing Technology CAS Beijing China School of Computer Science and Technology University of Chinese Academy of Sciences Beijing China State Key Laboratory of Information Security Institute of Information Engineering CAS Beijing China School of Cyber Security University of Chinese Academy of Sciences Beijing China Alibaba Group Beijing China Key Laboratory of Big Data Mining and Knowledge Management Chinese Academy of Sciences Beijing China Artificial Intelligence Research Center Peng Cheng Laboratory Shenzhen China

It is well-known that deep learning models are vulnerable to adversarial examples. Existing studies of adversarial training have made great progress against this challenge. As a typical trait, they often assume that the class distribution is overall balanced. However, long-tail datasets are ubiquitous in a wide spectrum of applications, where the amount of head class instances is larger than the tail classes. Under such a scenario, AUC is a much more reasonable metric than accuracy since it is insensitive toward class distribution. Motivated by this, we present an early trial to explore adversarial training methods to optimize AUC. The main challenge lies in that the positive and negative examples are tightly coupled in the objective function. As a direct result, one cannot generate adversarial examples without a full scan of the dataset. To address this issue, based on a concavity regularization scheme, we reformulate the AUC optimization problem as a saddle point problem, where the objective becomes an instance-wise function. This leads to an end-to-end training protocol. Furthermore, we provide a convergence guarantee of the proposed algorithm. Our analysis differs from the existing studies since the algorithm is asked to generate adversarial examples by calculating the gradient of a min-max problem. Finally, the extensive experimental results show the performance and robustness of our algorithm in three long-tail datasets. © 2022, CC BY.

关键词： Deep learning

来源：评论

学校读者我要写书评

暂无评论

DRL-M4MR: An Intelligent Multicast Routing Approach Based on DQN Deep Reinforcement Learning in SDN

arXiv

引用

arXiv 2022年

作者： Zhao, Chenwei Ye, Miao Xue, Xingsi Lv, Jianhui Jiang, Qiuxiang Wang, Yong School of Information and Communication Guilin University of Electronic Technology Guilin541004 China Guangxi Key Laboratory of Wireless Wideband Communication and Signal Processing Guilin University of Electronic Technology Guilin541004 China Fujian Provincial Key Laboratory of Big Data Mining and Applications Fujian University of Technology Fujian Fuzhou350118 China Peng Cheng Lab. Guangdong Shenzhen518038 China School of Computer Science and Information Security Guilin University of Electronic Technology Guilin541004 China

Traditional multicast routing methods have some problems in constructing a multicast tree, such as limited access to network state information, poor adaptability to dynamic and complex changes in the network, and inflexible data forwarding. To address these defects, the optimal multicast routing problem in software-defined networking (SDN) is tailored as a multi-objective optimization problem, and an intelligent multicast routing algorithm DRL-M4MR based on the deep Q network (DQN) deep reinforcement learning (DRL) method is designed to construct a multicast tree in SDN. First, the multicast tree state matrix, link bandwidth matrix, link delay matrix, and link packet loss rate matrix are designed as the state space of the DRL agent by combining the global view and control of the SDN. Second, the action space of the agent is all the links in the network, and the action selection strategy is designed to add the links to the current multicast tree under four cases. Third, single-step and final reward function forms are designed to guide the intelligence to make decisions to construct the optimal multicast tree. The experimental results show that, compared with existing algorithms, the multicast tree construct by DRL-M4MR can obtain better bandwidth, delay, and packet loss rate performance after training, and it can make more intelligent multicast routing decisions in a dynamic network environment. Copyright © 2022, The Authors. All rights reserved.

关键词： Reinforcement learning

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：