检索结果-内蒙古大学图书馆

38th Conference on Neural Information Processing systems, NeurIPS 2024

作者： Zeng, Xianzhi Jiang, Wenchao Zhang, Shuhao National Engineering Research Center for Big DataTechnology and System Services Computing Technology and System Lab Cluster and Grid Computing Lab School of Computer Science and Technology Huazhong University of Science and Technology Wuhan430074 China Nanyang Technological University Singapore Singapore University of Technology and Design Singapore

Matrix multiplication (MM) is pivotal in fields from deep learning to scientific computing, driving the quest for improved computational efficiency. Accelerating MM encompasses strategies like complexity reduction, parallel and distributed computing, hardware acceleration, and approximate computing techniques, namely AMM algorithms. Amidst growing concerns over the resource demands of large language models (LLMs), AMM has garnered renewed focus. However, understanding the nuances that govern AMM's effectiveness remains incomplete. This study delves into AMM by examining algorithmic strategies, operational specifics, dataset characteristics, and their application in real-world tasks. Through comprehensive testing across diverse datasets and scenarios, we analyze how these factors affect AMM's performance, uncovering that the selection of AMM approaches significantly influences the balance between efficiency and accuracy, with factors like memory access playing a pivotal role. Additionally, dataset attributes are shown to be vital for the success of AMM in applications. Our results advocate for tailored algorithmic approaches and careful strategy selection to enhance AMM's effectiveness. To aid in the practical application and ongoing research of AMM, we introduce LibAMM -a toolkit offering a wide range of AMM algorithms, benchmarks, and tools for experiment management. LibAMM aims to facilitate research and application in AMM, guiding future developments towards more adaptive and context-aware computational solutions. © 2024 Neural information processing systems foundation. All rights reserved.

关键词：

来源：评论

学校读者我要写书评

暂无评论

A comprehensive survey of visible infrared person re-identification from an application perspective

引用

Multimedia Tools and Applications 2024年第42期83卷 90243-90270页

作者： Chang, Hua Xu, Xin Liu, Wei Lu, Lingyi Li, Weigang School of Computer Science and Technology Wuhan University of Science and Technology Wuhan China Hubei Province Key Laboratory of Intelligent Information Processing and Real-time Industrial System Wuhan University of Science and Technology Wuhan430065 China School of Information Science and Engineering Wuhan University of Science and Technology Wuhan China

Person re-identification (ReID) is a significant issue in computer vision, aiming to match the same pedestrian across various cameras. Recent research on this issue has successfully reached a satisfactory performance level in the daytime scenario. However, the performance of ReID in low illumination scenarios suffers a dramatic degradation due to the insufficient personal information captured by visible cameras in low or no light scenarios. To address this challenge, the adoption of novel camera technologies for more effective pedestrian data is imperative. Owing to the constraints of distance and usage scenarios in deploying depth cameras, practical infrared cameras are frequently utilized, spurring research in visible infrared person re-identification (VI-ReID). Significant progress has been made in the field of VI-ReID in recent years, but only a few reviews have categorized this problem based on methodology. This article offers a novel perspective by classifying VI-ReID according to application scenarios. Following our categorization scheme, the main advancements in deep learning for VI-ReID over the past five years have been grouped into three categories as follows: retrieval of infrared images using visible images (V→IR), retrieval of visible images using infrared images (IR→V), and joint retrieval of infrared and visible images (V→IR and IR→V). Next, this survey outlines the available datasets and evaluation metrics. After that, we categorize diverse methodologies under the proposed classification and assess their performance metrics across common datasets. Finally, we present two prospective avenues for future research in this domain, informed by the current state of advancement. © The Author(s), under exclusive licence to Springer science+Business Media, LLC, part of Springer Nature 2024.

关键词： Infrared imaging

来源：评论

学校读者我要写书评

暂无评论

Unlearnable 3D Point Clouds: Class-wise Transformation Is All You Need 38

Unlearnable 3D Point Clouds: Class-wise Transformation Is Al...

引用

38th Conference on Neural Information Processing systems, NeurIPS 2024

作者： Wang, Xianlong Li, Minghui Liu, Wei Zhang, Hangtao Hu, Shengshan Zhang, Yechao Zhou, Ziqi Jin, Hai National Engineering Research Center for Big Data Technology and System China Services Computing Technology and System Lab China Cluster and Grid Computing Lab China Hubei Engineering Research Center on Big Data Security China Hubei Key Laboratory of Distributed System Security China School of Cyber Science and Engineering Huazhong University of Science and Technology China School of Software Engineering Huazhong University of Science and Technology China School of Computer Science and Technology Huazhong University of Science and Technology China

Traditional unlearnable strategies have been proposed to prevent unauthorized users from training on the 2D image data. With more 3D point cloud data containing sensitivity information, unauthorized usage of this new type data has also become a serious concern. To address this, we propose the first integral unlearnable framework for 3D point clouds including two processes: (i) we propose an unlearnable data protection scheme, involving a class-wise setting established by a category-adaptive allocation strategy and multi-transformations assigned to samples;(ii) we propose a data restoration scheme that utilizes class-wise inverse matrix transformation, thus enabling authorized-only training for unlearnable data. This restoration process is a practical issue overlooked in most existing unlearnable literature, i.e., even authorized users struggle to gain knowledge from 3D unlearnable data. Both theoretical and empirical results (including 6 datasets, 16 models, and 2 tasks) demonstrate the effectiveness of our proposed unlearnable framework. Our code is available at https://***/CGCL-codes/UnlearnablePC. © 2024 Neural information processing systems foundation. All rights reserved.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Adaptive Bistable Stochastic Resonance Based Weak Signal Reception in Additive Laplacian Noise

引用

China Communications 2024年第1期21卷 228-241页

作者： Jin Liu Zan Li Qiguang Miao Li Yang School of Computer Science and Technology Xidian UniversityXi’an 710071China State Key Laboratory of Integrated Services Networks Xidian UniversityXi’an 710071China

Weak signal reception is a very important and challenging problem for communication systems especially in the presence of non-Gaussian noise,and in which case the performance of optimal linear correlated receiver degrades *** at this,a novel uncorrelated reception scheme based on adaptive bistable stochastic resonance(ABSR)for a weak signal in additive Laplacian noise is *** analyzing the key issue that the quantitative cooperative resonance matching relationship between the characteristics of the noisy signal and the nonlinear bistable system,an analytical expression of the bistable system parameters is *** this basis,by means of bistable system parameters self-adaptive adjustment,the counterintuitive stochastic resonance(SR)phenomenon can be easily generated at which the random noise is changed into a benefit to assist signal ***,it is demonstrated that approximately 8dB bit error ratio(BER)performance improvement for the ABSR-based uncorrelated receiver when compared with the traditional uncorrelated receiver at low signal to noise ratio(SNR)conditions varying from-30dB to-5dB.

关键词： adaptive bistable stochastic resonance additive Laplacian noise low signal to noise ratio uncorrelated reception scheme weak signal reception

来源：评论

学校读者我要写书评

暂无评论

Multi-level Multi-task representation learning with adaptive fusion for multimodal sentiment analysis

引用

Neural computing and Applications 2025年第3期37卷 1491-1508页

作者： Zhu, Chuanbo Chen, Min Li, Haomin Zhang, Sheng Liang, Han Sun, Chao Liu, Yifan Chen, Jincai Wuhan National Laboratory for Optoelectronics Huazhong University of Science and Technology Hubei Wuhan430074 China School of Computer Science and Engineering South China University of Technology Guangdong Guangzhou510641 China Pazhou Laboratory Guangdong Guangzhou510640 China School of Computer Science and Technology Huazhong University of Science and Technology Hubei Wuhan430074 China Key Laboratory of Information Storage System Ministry of Education of China Hubei Wuhan430074 China

Multimodal sentiment analysis is an active task in multimodal intelligence, which aims to compute the user’s sentiment tendency from multimedia data. Generally, each modality is a specific and necessary perspective to express human sentiment, providing complementary and consensus information unavailable in a single modality. Nevertheless, the heterogeneous multimedia data often contain inconsistent and conflicting sentiment semantics that limits the model performance. In this work, we propose a Multi-level Multi-task Representation Learning with Adaptive Fusion (MuReLAF) network to bridge the semantic gap among different modalities. Specifically, we design a modality adaptive fusion block to adjust modality contributions dynamically. Besides, we build a multi-level multimodal representations framework to obtain modality-specific and modality-shared semantics by the multi-task learning strategy, where modality-specific semantics contain complementary information and modality-shared semantics include consensus information. Extensive experiments are conducted on four publicly available datasets: MOSI, MOSEI, SIMS, and SIMSV2(s), demonstrating that our model exhibits superior or comparable performance to state-of-the-art models. The achieved accuracies are 86.28%, 86.07%, 84.46%, and 82.78%, respectively, showcasing improvements of 0.82%, 0.84%, 1.75%, and 1.83%. Further analyses also indicate the effectiveness of our model in sentiment analysis. © The Author(s), under exclusive licence to Springer-Verlag London Ltd., part of Springer Nature 2024.

关键词： Multi-task learning

来源：评论

学校读者我要写书评

暂无评论

Intersecting-Boundary-Sensitive Fingerprinting for Tampering Detection of DNN Models 41

Intersecting-Boundary-Sensitive Fingerprinting for Tampering...

引用

41st International Conference on Machine Learning, ICML 2024

作者： Bai, Xiaofan He, Chaoxiang Ma, Xiaojing Zhu, Bin Benjamin Jin, Hai School of Cyber Science and Engineering Huazhong University of Science and Technology China National Engineering Research Center for Big Data Technology and System China Services Computing Technology and System Lab China Hubei Engineering Research Center on Big Data Security China Hubei Key Laboratory of Distributed System Security China Microsoft United States School of Computer Science and Technology Huazhong University of Science and Technology China Cluster and Grid Computing Lab China

Cloud-based AI services offer numerous benefits but also introduce vulnerabilities, allowing for tampering with deployed DNN models, ranging from injecting malicious behaviors to reducing computing resources. Fingerprint samples are generated to query models to detect such tampering. In this paper, we present Intersecting-Boundary-Sensitive Fingerprinting (IBSF), a novel method for black-box integrity verification of DNN models using only top-1 labels. Recognizing that tampering with a model alters its decision boundary, IBSF crafts fingerprint samples from normal samples by maximizing the partial Shannon entropy of a selected subset of categories to position the fingerprint samples near decision boundaries where the categories in the subset intersect. These fingerprint samples are almost indistinguishable from their source samples. We theoretically establish and confirm experimentally that these fingerprint samples' expected sensitivity to tampering increases with the cardinality of the subset. Extensive evaluation demonstrates that IBSF surpasses existing state-of-the-art fingerprinting methods, particularly with larger subset cardinality, establishing its state-of-the-art performance in black-box tampering detection using only top-1 labels. The IBSF code is available at: https://***/CGCL-codes/IBSF. Copyright 2024 by the author(s)

关键词： HTTP

来源：评论

学校读者我要写书评

暂无评论

Ciphertext-Policy Attribute-Based Encryption with Short Keys

引用

Chinese Journal of Electronics 2025年第4期23卷 655-660页

作者： Peng Xu Yong Tang Wenbin Jiang Hai Jin Deqing Zou Services Computing Technology and System Lab Cluster and Grid Computing Lab School of Computer Science and Technology Huazhong University of Science and Technology Wuhan China

Ciphertext-policy attribute-based encryption (CP-ABE) allows a user with some attributes to decrypt the ciphertexts associated with these attributes. Though several CP-ABE schemes with the constant size ciphertext were proposed to reduce the communication cost, their master public and secret keys still have the size linear in the total number of attributes. These schemes are unpractical for the attribute-scalable and many-attributes scenario. A new CP-ABE scheme is proposed. Each attribute is mapped to a mathematical value by a combination method. The master public and secret keys of the proposed CP-ABE scheme have the size linear in the binary size of a hash function's range. It has the comparable performance with existing schemes in the aspects like the time costs of encryption and decryption, the expressiveness of access policy and the provable security.

关键词： Costs Encryption

来源：评论

学校读者我要写书评

暂无评论

Towards High-throughput and Low-latency Billion-scale Vector Search via CPU/GPU Collaborative Filtering and Re-ranking 23

Towards High-throughput and Low-latency Billion-scale Vector...

引用

23rd USENIX Conference on File and Storage Technologies, FAST 2025

作者： Tian, Bing Liu, Haikun Tang, Yuhang Xiao, Shihai Duan, Zhuohui Liao, Xiaofei Jin, Hai Zhang, Xuecang Zhu, Junhua Zhang, Yu National Engineering Research Center for Big Data Technology and System Service Computing Technology and System Lab/Cluster and Grid Computing Lab School of Computer Science and Technology Huazhong University of Science and Technology China Huawei Technologies Co. Ltd. China

ISBN: (纸本)9781939133458

Approximate nearest neighbor search (ANNS) has emerged as a crucial component of database and AI infrastructure. Ever-increasing vector datasets pose significant challenges in terms of performance, cost, and accuracy for ANNS services. None of modern ANNS systems can address these issues simultaneously. In this paper, we present FusionANNS, a high-throughput, low-latency, cost-efficient, and high-accuracy ANNS system for billion-scale datasets using SSDs and only one entry-level GPU. The key idea of FusionANNS lies in CPU/GPU collaborative filtering and re-ranking mechanisms, which significantly reduce I/O operations across CPUs, GPU, and SSDs to break through the I/O performance bottleneck. Specifically, we propose three novel designs: (1) multi-tiered indexing to avoid data swapping between CPUs and GPU, (2) heuristic re-ranking to eliminate unnecessary I/Os and computations while guaranteeing high accuracy, and (3) redundant-aware I/O deduplication to further improve I/O efficiency. We implement FusionANNS and compare it with the state-of-the-art SSD-based ANNS system-SPANN and GPU-accelerated in-memory ANNS system-RUMMY. Experimental results show that FusionANNS achieves 1) 9.4-13.1× higher query per second (QPS) and 5.7-8.8× higher cost efficiency compared with SPANN;2) and 2-4.9× higher QPS and 2.3-6.8× higher cost efficiency compared with RUMMY, while guaranteeing low latency and high accuracy. © 2025 FAST. All Rights Reserved.

关键词： Collaborative filtering

来源：评论

学校读者我要写书评

暂无评论

DarkSAM: Fooling Segment Anything Model to Segment Nothing 38

DarkSAM: Fooling Segment Anything Model to Segment Nothing

引用

38th Conference on Neural Information Processing systems, NeurIPS 2024

作者： Zhou, Ziqi Song, Yufei Li, Minghui Hu, Shengshan Wang, Xianlong Zhang, Leo Yu Yao, Dezhong Jin, Hai National Engineering Research Center for Big Data Technology and System China Services Computing Technology and System Lab China Cluster and Grid Computing Lab China Hubei Engineering Research Center on Big Data Security China Hubei Key Laboratory of Distributed System Security China School of Computer Science and Technology Huazhong University of Science and Technology China School of Cyber Science and Engineering Huazhong University of Science and Technology China School of Software Engineering Huazhong University of Science and Technology China School of Information and Communication Technology Griffith University Australia

Segment Anything Model (SAM) has recently gained much attention for its outstanding generalization to unseen data and tasks. Despite its promising prospect, the vulnerabilities of SAM, especially to universal adversarial perturbation (UAP) have not been thoroughly investigated yet. In this paper, we propose DarkSAM, the first prompt-free universal attack framework against SAM, including a semantic decoupling-based spatial attack and a texture distortion-based frequency attack. We first divide the output of SAM into foreground and background. Then, we design a shadow target strategy to obtain the semantic blueprint of the image as the attack target. DarkSAM is dedicated to fooling SAM by extracting and destroying crucial object features from images in both spatial and frequency domains. In the spatial domain, we disrupt the semantics of both the foreground and background in the image to confuse SAM. In the frequency domain, we further enhance the attack effectiveness by distorting the high-frequency components (i.e., texture information) of the image. Consequently, with a single UAP, DarkSAM renders SAM incapable of segmenting objects across diverse images with varying prompts. Experimental results on four datasets for SAM and its two variant models demonstrate the powerful attack capability and transferability of DarkSAM. Our codes are available at: https://***/CGCL-codes/DarkSAM. © 2024 Neural information processing systems foundation. All rights reserved.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Numerical Simulation Study of Oil-Water Emulsion Separation in an Ultrasonic Field:Effect of Coupling between Acoustic and Flow Field Parameters

引用

China Petroleum Processing & Petrochemical technology 2024年第1期26卷 116-125页

作者： Wang Heping Lin Yinchao Li Yanggui Zhang Xiaohang Wu Yi Key Laboratory of Engineering Mathematics and Advanced Computing of Nanchang Institute of Technology School of SciencesNanchang Institute of TechnologyNanchang 330099People’s Republic of China Dongguan Key Laboratory of Kunpeng Computing School of Computer ScienceGuangdong University of Science&TechnologyDongguan 523083China State Key Laboratory of Plateau Ecology and Agriculture Qinghai UniversityXining 810016China

In this study,the separation and coalescence of oil-in-water emulsions are explored in an ultrasonic field using the lattice Boltzmann *** simulating the propagation of ultrasonic waves,this study focuses on examining the effects of acoustic wave frequency,the ratio of oil to water components,and the aspect ratio of the boundary on the emulsification and separation processes of oil-water *** following conclusions are drawn.①Frequency affects the speed of oil droplet separation,leading to an increase in droplet size over *** droplets are found near the source,while smaller droplets are distributed throughout the wave web.②As the boundary aspect ratio increases,the emulsification efficiency of the droplets weakens,and the system takes longer to stabilize.③Emulsions with a higher component of oil can better resist acoustic waves.④At the same acoustic frequency,longer wavelength ultrasonic fields promote the formation of uniformly distributed,smaller oil droplets,which is beneficial to the storage of *** numerical simulation results offer insights for optimizing conditions for oil-in-water separation and serve as a numerical reference for the study of oil-in-water emulsion separation in ultrasonic environments.

关键词： lattice Boltzmann method phase separation ultrasound field

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：