检索结果-内蒙古大学图书馆

arXiv 2023年

作者： Wu, Xiao-Ming Zheng, Dian Liu, Zuhao Zheng, Wei-Shi School of Computer Science and Engineering Sun Yat-sen University China Pengcheng Lab China Guangdong Province Key Laboratory of Information Security Technology China Key Laboratory of Machine Intelligence and Advanced Computing Ministry of Education China

Binarization of neural networks is a dominant paradigm in neural networks compression. The pioneering work BinaryConnect uses Straight Through Estimator (STE) to mimic the gradients of the sign function, but it also causes the crucial inconsistency problem. Most of the previous methods design different estimators instead of STE to mitigate it. However, they ignore the fact that when reducing the estimating error, the gradient stability will decrease concomitantly. These highly divergent gradients will harm the model training and increase the risk of gradient vanishing and gradient exploding. To fully take the gradient stability into consideration, we present a new perspective to the BNNs training, regarding it as the equilibrium between the estimating error and the gradient stability. In this view, we firstly design two indicators to quantitatively demonstrate the equilibrium phenomenon. In addition, in order to balance the estimating error and the gradient stability well, we revise the original straight through estimator and propose a power function based estimator, Rectified Straight Through Estimator (ReSTE for short). Comparing to other estimators, ReSTE is rational and capable of flexibly balancing the estimating error with the gradient stability. Extensive experiments on CIFAR-10 and ImageNet datasets show that ReSTE has excellent performance and surpasses the state-of-the-art methods without any auxiliary modules or losses. Copyright © 2023, The Authors. All rights reserved.

关键词： Stability

来源：评论

学校读者我要写书评

暂无评论

Estimator Meets Equilibrium Perspective: A Rectified Straight Through Estimator for Binary Neural Networks Training

Estimator Meets Equilibrium Perspective: A Rectified Straigh...

引用

International Conference on Computer Vision (ICCV)

作者： Xiao-Ming Wu Dian Zheng Zuhao Liu Wei-Shi Zheng School of Computer Science and Engineering Sun Yat-sen University China Pengcheng Lab China Guangdong Province Key Laboratory of Information Security Technology China Key Laboratory of Machine Intelligence and Advanced Computing Ministry of Education China

关键词：

来源：评论

学校读者我要写书评

暂无评论

A biosensing system using a multiparameter nonlinear dynamic analysis of cardiomyocyte beating for drug-induced arrhythmia recognition

引用

Microsystems & Nanoengineering 2022年第3期8卷 277-290页

作者： Hao Wang Yue Wu Quchao Zou Wenjian Yang Zhongyuan Xu Hao Dong Zhjing Zhu Depeng Wang Tanxing Wang Ning Hu Diming Zhang State Key Laboratory of Optoelectronic Materials and Technologies Guangdong Province Key Laboratory of Display Material and TechnologySchool of Electronics and Information TechnologySun Yat-sen UniversityGuangzhou 510006China Research Center for Itelligent Sensing Systems Zhejiang LabHangzhou 311121China ZJU-Hangzhou Global Scientific and Technological Innovation Center Department of ChemistryThe Second Affiliated Hospital Zhejiang University School of MedicineDepartment of Clinical Medical EngineeringZhejiang UniversityHangzhou 310058China Key Laboratory of Novel Target and Drug Study for Neural Repair of Zhejang Province School of MedicineSchool of Computer&Computing ScienceZhejiang University City CollegeHangzhou 310015China School of Brain Science and Brain Medicine Zhejiang UniversityHangzhou 310058China College of Energy and Power Engineering Nanjing University of Aeronautics and AstronauticsNanjing 210016China E-LinkCare Meditech Co LtdHangzhou 310011China State Key Laboratory of Transducer Technology Chinese Academy of SciencesShanghai 200050China

Cardiovascular disease is the number one cause of death in ***,cardiotoxicity is one of the most important adverse effects assessed by arrhythmia recognition in drug ***,cell-based techniques developed for arhythmia recognition primarily employ linear methods such as time-domain analysis that detect and compare individual waveforms and thus fall short in some applications that require automated and efficient arrhythmia recognition from large *** carried out the frst report to develop a biosensing system that integrated impedance measurement and multiparameter nonlinear dynamic algorithm(MNDA)analysis for druginduced arrhythmia recognition and *** biosensing system cultured cardiomyocytes as physiologically relevant models,used interdigitated electrodes to detect the mechanical beating of the cardiomyocytes,and employed MNDA analysis to recognize drug-induced arrhythmia from the cardiomyocyte beating *** best performing MNDA parameter,approximate entropy,enabled the system to recognize the appearance of sertindoleand norepinephrine-induced arrhythmia in the *** MNDA reconstruction in phase space enabled the system to classify the different arrhythmias and quantify the severity of *** new biosensing system utilizing MNDA provides a promising and alternative method for drug-induced arrhythmia recognition and classification in cardiological and pharmaceutical applications.

关键词： arrhythmia cardio analysis

来源：评论

学校读者我要写书评

暂无评论

Gray Learning from Non-IID Data with Out-of-distribution Samples

arXiv

引用

arXiv 2022年

作者： Zhao, Zhilin Cao, Longbing Wang, Chang-Dong The Data Science Lab School of Computing and DataX Research Centre Macquarie University SydneyNSW2109 Australia The School of Computer Science and Engineering Sun Yat-sen University Guangzhou China Guangdong Province Key Laboratory of Computational Science Guangzhou China Key Laboratory of Machine Intelligence and Advanced Computing Ministry of Education China

The integrity of training data, even when annotated by experts, is far from guaranteed, especially for non-IID datasets comprising both in- and out-of-distribution samples. In an ideal scenario, the majority of samples would be in-distribution, while samples that deviate semantically would be identified as out-of-distribution and excluded during the annotation process. However, experts may erroneously classify these out-of-distribution samples as in-distribution, assigning them labels that are inherently unreliable. This mixture of unreliable labels and varied data types makes the task of learning robust neural networks notably challenging. We observe that both in- and out-of-distribution samples can almost invariably be ruled out from belonging to certain classes, aside from those corresponding to unreliable ground-truth labels. This opens the possibility of utilizing reliable complementary labels that indicate the classes to which a sample does not belong. Guided by this insight, we introduce a novel approach, termed Gray Learning (GL), which leverages both ground-truth and complementary labels. Crucially, GL adaptively adjusts the loss weights for these two label types based on prediction confidence levels. By grounding our approach in statistical learning theory, we derive bounds for the generalization error, demonstrating that GL achieves tight constraints even in non-IID settings. Extensive experimental evaluations reveal that our method significantly outperforms alternative approaches grounded in robust statistics. Copyright © 2022, The Authors. All rights reserved.

关键词： Machine learning

来源：评论

学校读者我要写书评

暂无评论

Text-adaptive multiple visual prototype matching for video-text retrieval 22

Text-adaptive multiple visual prototype matching for video-t...

引用

Proceedings of the 36th International Conference on Neural Information Processing Systems

作者： Chengzhi Lin Ancong Wu Junwei Liang Jun Zhang Wenhang Ge Wei-Shi Zheng Chunhua Shen School of Computer Science and Engineering Sun Yat-sen University China AI Thrust Hong Kong University of Science and Technology (Guangzhou) Tencent Youtu Lab School of Computer Science and Engineering Sun Yat-sen University China and Guangdong Province Key Laboratory of Information Security PR China and Key Laboratory of Machine Intelligence and Advanced Computing Ministry of Education China Zhejiang University

ISBN: (纸本)9781713871088

Cross-modal retrieval between videos and texts has gained increasing research interest due to the rapid emergence of videos on the web. Generally, a video contains rich instance and event information and the query text only describes a part of the information. Thus, a video can correspond to multiple different text descriptions and queries. We call this phenomenon the "Video-Text Correspondence Ambiguity" problem. Current techniques mostly concentrate on mining local or multi-level alignment between contents of a video and text (e.g., object to entity and action to verb). It is difficult for these methods to alleviate the video-text correspondence ambiguity by describing a video using only one single feature, which is required to be matched with multiple different text features at the same time. To address this problem, we propose a Text-Adaptive Multiple Visual Prototype Matching model, which automatically captures multiple prototypes to describe a video by adaptive aggregation of video token features. Given a query text, the similarity is determined by the most similar prototype to find correspondence in the video, which is termed text-adaptive matching. To learn diverse prototypes for representing the rich information in videos, we propose a variance loss to encourage different prototypes to attend to different contents of the video. Our method outperforms the state-of-the-art methods on four public video retrieval datasets.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Abnormality Detection in Chest X-Ray Images Using Uncertainty Prediction Autoencoders 23rd

Abnormality Detection in Chest X-Ray Images Using Uncertaint...

引用

23rd International Conference on Medical Image computing and Computer-Assisted Intervention, MICCAI 2020

作者： Mao, Yifan Xue, Fei-Fei Wang, Ruixuan Zhang, Jianguo Zheng, Wei-Shi Liu, Hongmei School of Data and Computer Science Sun Yat-sen University Guangzhou China Key Laboratory of Machine Intelligence and Advanced Computing MOE Guangzhou China Department of Computer Science and Engineering Southern University of Science and Technology Shenzhen China Pazhou Lab Guangzhou China Guangdong Province Key Laboratory of Information Security Technology Guangzhou China

ISBN: (纸本)9783030597245

Chest radiography is widely used in annual medical screening to check whether lungs are healthy or not. Therefore it would be desirable to develop an intelligent system to help clinicians automatically detect potential abnormalities in chest X-ray images. Here with only healthy X-ray images, we propose a new abnormality detection approach based on an autoencoder which outputs not only the reconstructed normal version of the input image but also a pixel-wise uncertainty prediction. Higher uncertainty often appears at normal region boundaries with relatively larger reconstruction errors, but not at potential abnormal regions in the lung area. Therefore the normalized reconstruction error by the uncertainty provides a natural measurement for abnormality detection in images. Experiments on two chest X-ray datasets show the state-of-the-art performance by the proposed approach. © 2020, Springer Nature Switzerland AG.

关键词： Forecasting

来源：评论

学校读者我要写书评

暂无评论

FakeScope: Large Multimodal Expert Model for Transparent AI-Generated Image Forensics

arXiv

引用

arXiv 2025年

作者： Li, Yixuan Tian, Yu Huang, Yipo Lu, Wei Wang, Shiqi Lin, Weisi Rocha, Anderson College of Computing City University of Hong Kong Hong Kong School of Computer Science and Engineering Ministry of Education Key Laboratory of Information Technology Guangdong Province Key Laboratory of Information Security Technology Sun Yat-Sen University Guangzhou510006 China College of Computing and Data Science Nanyang Technological University Singapore Artificial Intelligence Lab Recod.ai University of Campinas Campinas13084-851 Brazil

The rapid and unrestrained advancement of generative artificial intelligence (AI) presents a double-edged sword: while enabling unprecedented creativity, it also facilitates the generation of highly convincing deceptive content, undermining societal trust. As image generation techniques become increasingly sophisticated, detecting synthetic images is no longer just a binary task—it necessitates interpretable, context-aware methodologies that enhance trustworthiness and transparency. However, existing detection models primarily focus on classification, offering limited explanatory insights into image authenticity. In this work, we propose FakeScope, an expert multimodal model (LMM) tailored for AI-generated image forensics, which not only identifies AI-synthetic images with high accuracy but also provides rich, interpretable, and query-driven forensic insights. To this end, we first construct FakeChain dataset that contains linguistic authenticity reasoning based on visual trace evidence, developed through a novel human-machine collaborative framework. Building upon it, we further present FakeInstruct, the largest multimodal instruction tuning dataset containing 2 million visual instructions tailored to enhance forensic awareness in LMMs. Leveraging the knowledge of FakeInstruct, FakeScope achieves state-of-the-art performance in both closed-ended and open-ended forensic scenarios. It can distinguish synthetic images with high accuracy while offering coherent and insightful explanations, free-form discussions on fine-grained forgery attributes, and actionable enhancement strategies. Notably, despite being trained exclusively on qualitative hard labels, FakeScope demonstrates remarkable zero-shot quantitative capability on detection, enabled by our proposed token-based probability estimation strategy. Furthermore, FakeScope exhibits strong generalization and in-the-wild ability, ensuring its applicability in real-world scenarios. The data, model, and demo will be publ

关键词： Computer forensics

来源：评论

学校读者我要写书评

暂无评论

Collective dynamics and control for multiple unmanned surface vessels

arXiv

引用

arXiv 2019年

作者： Liu, Bin Chen, Zhiyong Zhang, Hai-Tao Wang, Xudong Geng, Tao Su, Housheng Zhao, Jin Guangdong HUST Industrial Technology Research Institute Guangdong Province Key Lab of Digital Manufacturing Equipment Dongguan523808 China School of Electrical Engineering and Computing University of Newcastle CallaghanNSW2308 Australia School of Automation State Key Lab of Digital Manufacturing Equipment and Technology Key Lab of Imaging Processing and Intelligence Control Huazhong University of Science and Technology Wuhan430074 China School of Automation Key Lab of Imaging Processing and Intelligence Control Huazhong University of Science and Technology Wuhan430074 China

A multi-unmanned surface vessel (USV) formation control system is established on a novel platform composed of three 1.2 meter-long hydraulic jet propulsion surface vessels, a differential GPS reference station, and inter-vessel Zigbee communication modules. The system is also equipped with an upper level collective multi-USV protocol and a lower level vessel dynamics controller. The system is capable of chasing and surrounding a target vessel. The results are supported by rigorous theoretical analysis in terms of asymptotical surrounding behavior and trajectory regulation. Extensive experiments are conducted to demonstrate the effectiveness and efficiency of the proposed hardware and software architectures. Copyright © 2019, The Authors. All rights reserved.

关键词： Unmanned surface vehicles

来源：评论

学校读者我要写书评

暂无评论

DBFT: A Byzantine Fault Tolerant Protocol with Graceful Performance Degradation

DBFT: A Byzantine Fault Tolerant Protocol with Graceful Perf...

引用

Reliable Distributed Systems

作者： Jingjing Zhang Yingyao Rong Jiannong Cao Chunming Rong Jing Bian Weigang Wu School of Data and Comp. Sci. Sun Yat-Sen University Guangzhou China Department of Computing Hong Kong Polytechnic University HongKong Electrical Engineering & Computer Science Department University of Stavanger Stavanger Norway Guangdong Province Key Lab of Big Data Analysis and Proc. Sun Yat-sen University Guangzhou China

ISBN: (数字)9781728142227

ISBN: (纸本)9781728142234

The surging interest in blockchain has revitalized the search for efficient Byzantine fault-tolerant (BFT) protocols, which are used for blockchains to achieve consensus among replicated data blocks. Most existing BFT protocols perform well in fault-free cases, but they usually suffer from serious performance degradation when faults occur. In this paper, we present DBFT, a BFT protocol that realizes graceful performance degradation in normal cases. The major novelty of DBFT lies in the double-response mechanism, which lets replica nodes deterministically respond to clients twice: one is after the speculative execution phase and the other is after the commitment phase. The double-response mechanism can handle inconsistency in speculative execution, so as to alleviate performance degradation caused by faults. Moreover, DBFT does not involve clients in critical consensus operations so as to reduce the load of clients. The correctness properties, i.e., safety and liveness, of DBFT is rigorously proved. The performance of DBFT is evaluated via experiments and the results show that, DBFT outperforms similar BFT protocols obviously in normal cases.

关键词： cryptographic protocols fault tolerance degradation of performance Fault tolerance cryptographic protocols speculative execution protocols customers Clients Reaction Mechanisms

来源：评论

学校读者我要写书评

暂无评论

Leveraging semantic labeling for question matching to facilitate question-answer archive reuse 1

引用

11th International Conference on Intelligent computing, ICIC 2015

作者： Hao, Tianyong Qiu, Xinying Jiang, Shengyi Key Lab of Language Engineering and Computing of Guangdong Province Guangdong University of Foreign Studies Guangzhou China Cisco School of Informatics Guangdong University of Foreign Studies Guangzhou China

ISBN: (数字)9783319221809

ISBN: (纸本)9783319221793

A new question representation method is proposed for automated question matching over accumulated question-answer data archive. The representation defines four kinds of question words as question-type words, user-centered words, shareable-pattern words, and irrelevant words for question analysis. These question words are further annotated by a semantic labeling ontology to enhance the semantic representation for the purpose of word ambiguity reduction. We tested the matching precision on 5,000 questions with respect to various generators and the result demonstrated the stability of the method. We further compared the method with Cosine similarity and WordNet-based semantic similarity as baselines on a standard TREC dataset containing 5,536 questions. The results presented that our method improved MRR by 8.6% and accuracy by 9.6% on average, indicating its effectiveness. © Springer International Publishing Switzerland 2015.

关键词： Ontology

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：