检索结果-内蒙古大学图书馆

2025 Design, Automation and Test in Europe Conference, DATE 2025

作者： Shi, Yizhou Li, Liying Zeng, Yue Cong, Peijin Zhou, Junlong Nanjing University National Key Laboratory for Novel Software Technology Nanjing210023 China School of Computer Science and Engineering Nanjing University of Science and Technology Nanjing210094 China Southeast University National Mobile Communications Research Laboratory Nanjing211111 China Key Laboratory of Embedded System and Service Computing Tongji University Ministry of Education Shanghai201804 China

ISBN: (纸本)9783982674100

Deep neural networks (DNNs) have demonstrated exceptional performance, leading to diverse applications across various mobile devices (MDs). Considering factors like portability and environmental sustainability, an increasing number of MDs are adopting energy harvesting (EH) techniques for power supply. However, the computational intensity of DNNs presents significant challenges for their deployment on these resource-constrained devices. Existing approaches often employ DNN partition or offloading to mitigate the time and energy consumption associated with running DNNs on MDs. Nonetheless, existing methods frequently fall short in accurately modeling the execution time of DNNs, and do not consider to use thread allocation for further latency and energy consumption optimization. To solve these problems, we propose a dynamic DNN partition and thread allocation method to optimize the latency and energy consumption of running DNNs on EH-enabled MDs. Specifically, we first investigate the relationship between DNN inference latency and allocated threads and establish an accurate DNN latency prediction model. Based on the prediction model, a DRL-based DNN partition (DDP) algorithm is designed to find the optimal partitions for DNNs. A thread allocation (TA) algorithm is proposed to reduce the inference latency. Experimental results from our test-bed platform demonstrate that compared to four benchmarking methods, our scheme can reduce DNN inference latency and energy consumption by up to 37.3% and 38.5%. © 2025 EDAA.

关键词： Energy utilization

来源：评论

学校读者我要写书评

暂无评论

High-Fidelity Diffusion Editor for Zero-Shot Text-Guided Video Editing 24

High-Fidelity Diffusion Editor for Zero-Shot Text-Guided Vid...

引用

24th IEEE International Conference on Data Mining, ICDM 2024

作者： Luo, Yan Zuo, Zhichao Zhang, Zhao Zhao, Zhongqiu Zhang, Haijun Hong, Richang School of Computer Science and Information Engineering Hefei University of Technology Hefei China Yunnan Key Laboratory of Software Engineering Yunan China School of Computer Science Harbin Institute of Technology Shenzhen China

ISBN: (纸本)9798331506681

Text-guided image generative diffusion models achieve fast development on the generation and editing of high-quality images. To extend such success to video editing, some efforts combining image generation with video editing have been made, which however only achieve inferior performance. We attribute it to two challenges: 1) different from the static image generation, it is tricky for dynamic video information to ensure the temporal fidelity of motion consistency across different frames;2) the randomness of the frame generation process makes it hard to continuously retain the similar spatial fidelity for the original detailed features. In this paper, we propose a new high-fidelity diffusion model-based zero-shot text-guided video editing network, called HiFiVEditor, which aims to conduct effective video editing with high fidelity of the original video's detailed and dynamic information. Specifically, we propose a Spatial-Temporal Fidelity Block (STFB) that enables the model to restore the spatial features by enlarging the spatial perceptual field to avoid loss of important information, and capture more dynamic information between different frames by using all frames for preserving temporal consistency to achieve better temporal fidelity. In addition, we introduce Null-Text Embedding to create a soft text embedding to optimize the noise learning process, so that the latent noise can be aligned with the prompt. Furthermore, to tune the video style and render it more realistic, we employ a Prior-Guided Perceptual Loss to constrain the prediction results to avoid deviating from the original video style. Extensive experiments demonstrate the superior video editing capability compared to existing works. © 2024 IEEE.

关键词： Video recording

来源：评论

学校读者我要写书评

暂无评论

Dual Cross-Stage Partial Learning for Detecting Objects in Dehazed Images 24

Dual Cross-Stage Partial Learning for Detecting Objects in D...

引用

24th IEEE International Conference on Data Mining, ICDM 2024

作者： Zhao, Jinbiao Zhang, Zhao Ren, Jiahuan Zhang, Haijun Zhao, Zhongqiu Wang, Meng School of Computer Science and Information Engineering Hefei University of Technology Hefei China Yunnan Key Laboratory of Software Engineering Yunan China Harbin Institute of Technology Department of Computer Science Shenzhen China

ISBN: (纸本)9798331506681

Performing an object detection task after the restoration of a hazy image, or rather detecting with the network backbone directly, will result in the inclusion of information mixed with dehazing, which tends to interfere with detection performance. To address these issues, we propose a novel framework for detecting objects in dehazed images via Dual Cross-Stage Partial Learning (DCSP). Specifically, we introduce a Cross-Stage Partial (CSP) module for extracting clean feature information after dehazing. Secondly, to enhance data integrity, we employ a skip-input strategy to supplement information related to object detection features that may be lost during the dehazing task, while avoiding the gradient vanishing problem. In addition, CSP is also introduced to facilitate comprehensive learning of multiple feature representations. Finally, to avoid the inclusion of irrelevant dehazing information in detection, we apply a Ground-Truth Flow at detection network (at dark3), for fine feature information calibration. Additionally, we created a synthetic fog dataset to expand the training data for DCSP. Experimental results on both synthetic and real-world datasets demonstrate the effectiveness and accuracy of the proposed method. The code is available at https://***/zhaojinbiao/DCSP. © 2024 IEEE.

关键词： Demulsification

来源：评论

学校读者我要写书评

暂无评论

AdvTTS: Adversarial Text-to-Speech Synthesis Attack on Speaker Identification Systems

AdvTTS: Adversarial Text-to-Speech Synthesis Attack on Speak...

引用

International Conference on Acoustics, Speech, and Signal Processing (ICASSP)

作者： Chu-Xiao Zuo Zhi-Jun Jia Wu-Jun Li Department of Computer Science and Technology National Key Laboratory for Novel Software Technology Nanjing University China

Speaker identification (SI) systems have been widely employed in real-world applications. However, recent research has demonstrated that SI systems are vulnerable to two prevalent attacks even without providing feedback to the attacker: the transfer-based adversarial attack and the speech synthesis spoofing attack. The transfer-based adversarial attack faces the challenges of collecting natural speech for specific content and timbre. In contrast, the speech synthesis spoofing attack can synthesize speech for any content and timbre but can be detected by audio deepfake detectors (ADD). In this paper, we propose a novel method, called adversarial text-to-speech synthesis (AdvTTS), for attacking SI systems. AdvTTS combines the strengths of transfer-based adversarial attacks and speech synthesis spoofing attacks, by synthesizing transferable attack speech with local surrogate models. AdvTTS is the first attack method that can conduct both adversarial and spoofing attacks with any speech content and timbre. AdvTTS can deceive SI systems with high-quality speech while evading ADD detection. Experiments show that AdvTTS can outperform other baselines for spoofing attacks, and can outperform the baselines for adversarial attacks with the combination of projected gradient descent (PGD).

关键词：

来源：评论

学校读者我要写书评

暂无评论

Convergence Analysis of Graphical Game-Based Nash Q-Learning using the Interaction Detection Signal of N-Step Return 48

Convergence Analysis of Graphical Game-Based Nash Q-Learning...

引用

48th IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP 2023

作者： Zhuang, Yunkai Yang, Shangdong Li, Wenbin Gao, Yang Nanjing University of Posts and Telecommunications Nanjing China Nanjing University State Key Laboratory for Novel Software Technology Nanjing China

ISBN: (纸本)9781728163277

The graphical game provides an effective method for modeling different kinds of sparse interactions in multi-agent reinforcement learning. Most previous work on game abstraction lacks theoretical guarantees of convergence. In this paper, we adopt the N-step return signal to detect interactions between agents and build the Markov graphical game based on it. We analyze that the solution of the Markov graphical game is an ϵ-Nash equilibrium which guarantees the convergence of the proposed NSR-G2NashQ algorithm theoretically. Also, we have done experiments in different multi-agent reinforcement learning tasks with both tabular and function approximation solutions. The results show the NSR-G2NashQ algorithm accelerates the convergence of agents to the optimal policy. © 2023 IEEE.

关键词： game abstraction Graphical game multi-agent reinforcement learning sparse interaction

来源：评论

学校读者我要写书评

暂无评论

Latency-First Smart Contract: Overclock the Blockchain for a while 42

Latency-First Smart Contract: Overclock the Blockchain for a...

引用

42nd IEEE International Conference on computer Communications, INFOCOM 2023

作者： Qi, Huayi Xu, Minghui Cheng, Xiuzhen Lyu, Weifeng Shandong University School of Computer Science and Technology China Beihang University State Key Laboratory of Software Development Environment China

ISBN: (纸本)9798350334142

Blockchain systems can become overwhelmed by a large number of transactions, leading to increased latency. As a consequence, latency-sensitive users must bid against each other and pay higher fees to ensure that their transactions are processed in priority. However, most of the time of a blockchain system (78% in Ethereum), there is still a lot of unused computational power, with few users sending transactions. To address this issue and reduce latency for users, we propose the latency-first smart contract model in this paper, which optimistically accepts committed transactions. This allows users to submit a commitment during times of high demand, and then complete the rest of the work at a lower priority. From the perspective of the blockchain, this temporarily "overclocks"the system. We have developed a programming tool for our model, and our experiments show that the proposed latency-first smart contract model can greatly reduce latency during the periods of high demand. © 2023 IEEE.

关键词： Smart contract

来源：评论

学校读者我要写书评

暂无评论

Test Case Classification via Few-Shot Learning 9

Test Case Classification via Few-Shot Learning

引用

9th International Conference on Dependable Systems and Their Applications, DSA 2022

作者： Zhao, Yuan Tang, Haojie Zhang, Quanjun Liu, Sining Wang, Jin Liu, Jia Nanjing University State Key Laboratory for Novel Software Technology Nanjing China

ISBN: (数字)9781665488778

ISBN: (纸本)9781665488778

Crowdsourcing testing can reduce testing costs and improve testing efficiency. However, crowdsourcing testing generates many test cases, from which testers need to select task-related test cases for execution. Furthermore, it is difficult to get the labeled test cases, and it is also costly to mark the test cases manually. Even in the set of labeled test cases, there is still an uneven distribution of labels. To address the difficulties mentioned above, this paper proposes a test case classification framework based on Few-shot Learning. The framework augments test cases and extracts relevant information for vectorization, collects the category lexicon of test cases using the BiLSTM model, and finally classifies the test cases. To verify the effectiveness of the classification framework, we selected thousands of test cases from three crowd testing projects to conduct in-usability evaluation experiments. The experimental results show that our classification method has a higher accuracy rate than existing classification methods. © 2022 IEEE.

关键词： Crowdsourcing

来源：评论

学校读者我要写书评

暂无评论

A Blockchain-enabled Secure Access Management Method in Edge Computing 29

A Blockchain-enabled Secure Access Management Method in Edge...

引用

29th IEEE International Conference on Parallel and Distributed Systems, ICPADS 2023

作者： Jiang, Xutong Zhang, Guoming Tian, Hao Xiang, Haolong Zhang, Xuyun Dou, Wanchun Nanjing University State Key Laboratory for Novel Software Technology Nanjing China Macquarie University School of Computing Sydney Australia

ISBN: (纸本)9798350330717

Edge computing has emerged as a transformative paradigm with applications ranging from IoT to smart homes and transportation systems. However, its decentralized nature presents significant challenges in securing sensitive data, particularly in scenarios involving data sharing. To address these issues, this paper introduces a secure data access control system for edge computing by leveraging blockchain to foster mutual trust among edge servers and employing attribute-based encryption for secure data sharing. Our proposed solution seeks to enhance data security in distributed environments. We validate our method through practical experiments conducted on multiple edge servers, confirming its effectiveness in safeguarding data integrity and privacy. © 2023 IEEE.

关键词： blockchain edge computing encryption security

来源：评论

学校读者我要写书评

暂无评论

Buffered asynchronous SGD for byzantine learning

引用

The Journal of Machine Learning Research 2023年第1期24卷 9761-9822页

作者： Yi-Rui Yang Wu-Jun Li National Key Laboratory for Novel Software Technology Department of Computer Science and Technology Nanjing University Nanjing China

Distributed learning has become a hot research topic due to its wide application in cluster-based large-scale learning, federated learning, edge computing, and so on. Most traditional distributed learning methods typically assume no failure or attack. However, many unexpected cases, such as communication failure and even malicious attack, may happen in real applications. Hence, Byzantine learning (BL), which refers to distributed learning with failure or attack, has recently attracted much attention. Most existing BL methods are synchronous, which are impractical in some applications due to heterogeneous or offline workers. In these cases, asynchronous BL (ABL) is usually preferred. In this paper, we propose a novel method, called buffered asynchronous stochastic gradient descent (BASGD), for ABL. To the best of our knowledge, BASGD is the first ABL method that can resist non-omniscient attacks without storing any instances on the server. Furthermore, we also propose an improved variant of BASGD, called BASGD with momentum (BASGDm), by introducing local momentum into BASGD. Compared with those methods which need to store instances on server, BASGD and BASGDm have a wider scope of application. Both BASGD and BASGDm are compatible with various aggregation rules. Moreover, both BASGD and BASGDm are proved to be convergent and able to resist failure or attack. Empirical results show that our methods significantly outperform existing ABL baselines when there exists failure or attack on workers.

关键词： distributed machine learning momentum asynchronous Byzantine learning buffer stochastic gradient descent

来源：评论

学校读者我要写书评

暂无评论

InfLoRA: Interference-Free Low-Rank Adaptation for Continual Learning

arXiv

引用

arXiv 2024年

作者： Liang, Yan-Shuo Li, Wu-Jun National Key Laboratory for Novel Software Technology Department of Computer Science and Technology Nanjing University China

Continual learning requires the model to learn multiple tasks sequentially. In continual learning, the model should possess the ability to maintain its performance on old tasks (stability) and the ability to adapt to new tasks continuously (plasticity). Recently, parameter-efficient fine-tuning (PEFT), which involves freezing a pre-trained model and injecting a small number of learnable parameters to adapt to downstream tasks, has gained increasing popularity in continual learning. Although existing continual learning methods based on PEFT have demonstrated superior performance compared to those not based on PEFT, most of them do not consider how to eliminate the interference of the new task on the old tasks, which inhibits the model from making a good trade-off between stability and plasticity. In this work, we propose a new PEFT method, called interference-free low-rank adaptation (InfLoRA), for continual learning. InfLoRA injects a small number of parameters to reparameterize the pre-trained weights and shows that fine-tuning these injected parameters is equivalent to fine-tuning the pre-trained weights within a subspace. Furthermore, InfLoRA designs this subspace to eliminate the interference of the new task on the old tasks, making a good trade-off between stability and plasticity. Experimental results show that InfLoRA outperforms existing state-of-the-art continual learning methods on multiple datasets. Code is available at https://***/liangyanshuo/InfLoRA. Copyright © 2024, The Authors. All rights reserved.

关键词： Economic and social effects

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：