检索结果-内蒙古大学图书馆

41st International Conference on Machine Learning, ICML 2024

作者： Zhou, Zhengyu Liu, Weiwei School of Computer Science National Engineering Research Center for Multimedia Software Institute of Artificial Intelligence Hubei Key Laboratory of Multimedia and Network Communication Engineering Wuhan University Wuhan China

Goodness-of-fit testing, a classical statistical tool, has been extensively explored in the batch setting, where the sample size is ***, practitioners often prefer methods that adapt to the complexity of a problem rather than fixing the sample size *** batch tests are generally unsuitable for streaming data, as valid inference after data peeking requires multiple testing corrections, resulting in reduced statistical *** address this issue, we delve into the design of consistent sequential goodness-of-fit *** the principle of testing by betting, we reframe this task as selecting a sequence of payoff functions that maximize the wealth of a fictitious bettor, betting against the null in a repeated *** conduct experiments to demonstrate the adaptability of our sequential test across varying difficulty levels of problems while maintaining control over type-I errors. Copyright 2024 by the author(s)

关键词：

来源：评论

学校读者我要写书评

暂无评论

Verifiable Attribute-Based Proxy Re-encryption with Non-repudiation Based on Blockchain 3rd

Verifiable Attribute-Based Proxy Re-encryption with Non-rep...

引用

3rd EAI International Conference on Blockchain Technology and Emerging Applications, BlockTEA 2023

作者： He, Yaorui Liang, Ting Huang, Pei Xia, Zhe School of Computer Science and Artificial Intelligence Wuhan University of Technology Wuhan430070 China Hubei Key Laboratory of Transportation Internet of Things Wuhan University of Technology Wuhan430071 China

ISBN: (纸本)9783031600364

With the development of Blockchain, cloud computing, and artificial intelligence, smart transportation is highly likely to drive urban transportation in the direction of intelligence and digitalization. However, when connected vehicle devices share data in edge networks, there are security and privacy issues, e.g. leakage of sensitive information will cause serious threats. The separation of user data ownership and physical control requires users to impose access control on the outsourced data. Existing privacy protection schemes still suffer from problems such as a lack of supervision of centralized third-party cloud servers, which face the challenge of data leakage. In this paper, Blockchain and proxy re-encryption techniques are used to address these challenges. To enable sharing of the outsourced data in a secure way, Attribute-Based Proxy Re-encryption (ABPRE) is a popular technique. At the same time, verifiability enables the shared user to verify that the re-encrypted ciphertext returned by the server is correct. In addition, the introduction of a decentralized Blockchain provides distributed storage and it is tamper-proof for enhancing the trustworthiness of the connected vehicle devices as well as the security of the communication between the entities. The security and performance analyses demonstrate that our proposed scheme can achieve the desirable security features and it is efficient for protecting data privacy. © ICST Institute for computer sciences, Social Informatics and Telecommunications Engineering 2024.

关键词： Network security

来源：评论

学校读者我要写书评

暂无评论

ULAREF: A Unified Label Refinement Framework for Learning with Inaccurate Supervision 41

ULAREF: A Unified Label Refinement Framework for Learning wi...

引用

41st International Conference on Machine Learning, ICML 2024

作者： Qiao, Congyu Xu, Ning Hu, Yihao Geng, Xin School of Computer Science and Engineering Southeast University Nanjing China Key Laboratory of New Generation Artificial Intelligence Technology and Its Interdisciplinary Applications Southeast University Ministry of Education China

Learning with inaccurate supervision is often encountered in weakly supervised learning, and researchers have invested a considerable amount of time and effort in designing specialized algorithms for different forms of annotations in inaccurate supervision. In fact, different forms of these annotations share the fundamental characteristic that they all still incorporate some portion of correct labeling information. This commonality can serve as a lever, enabling the creation of a cohesive framework designed to tackle the challenges associated with various forms of annotations in learning with inaccurate supervision. In this paper, we propose a unified label refinement framework named ULAREF, i.e., a Unified LAbel REfinement Framework for learning with inaccurate supervision, which is capable of leveraging label refinement to handle inaccurate supervision. Specifically, our framework trains the predictive model with refined labels through global detection of reliability and local enhancement using an enhanced model fine-tuned by a proposed consistency loss. Also, we theoretically justify that the enhanced model in local enhancement can achieve higher accuracy than the predictive model on the detected unreliable set under mild assumptions. Copyright 2024 by the author(s)

关键词： Self-supervised learning

来源：评论

学校读者我要写书评

暂无评论

Devil is in Details: Locality-Aware 3D Abdominal CT Volume Generation for Self-Supervised Organ Segmentation 24

Devil is in Details: Locality-Aware 3D Abdominal CT Volume G...

引用

32nd ACM International Conference on Multimedia, MM 2024

作者： Wang, Yuran Wan, Zhijing Qiu, Yansheng Wang, Zheng National Engineering Research Center for Multimedia Software Hubei Key Laboratory of Multimedia and Network Communication Engineering Institute of Artificial Intelligence School of Computer Science Wuhan University Wuhan China

ISBN: (纸本)9798400706868

In the realm of medical image analysis, self-supervised learning (SSL) techniques have emerged to alleviate labeling demands, while still facing the challenge of training data scarcity owing to escalating resource requirements and privacy constraints. Numerous efforts employ generative models to generate high-fidelity, unlabeled 3D volumes across diverse modalities and anatomical regions. However, the intricate and indistinguishable anatomical structures within the abdomen pose a unique challenge to abdominal CT volume generation compared to other anatomical regions. To address the overlooked challenge, we introduce the Locality-Aware Diffusion (Lad), a novel method tailored for exquisite 3D abdominal CT volume generation. We design a locality loss to refine crucial anatomical regions and devise a condition extractor to integrate abdominal priori into generation, thereby enabling the generation of large quantities of high-quality abdominal CT volumes essential for SSL tasks without the need for additional data such as labels or radiology reports. Volumes generated through our method demonstrate remarkable fidelity in reproducing abdominal structures, achieving a decrease in FID score from 0.0034 to 0.0002 on AbdomenCT-1K dataset, closely mirroring authentic data and surpassing current methods. Extensive experiments demonstrate the effectiveness of our method in self-supervised organ segmentation tasks, resulting in an improvement in mean Dice scores on two abdominal datasets effectively. These results underscore the potential of synthetic data to advance self-supervised learning in medical image analysis. © 2024 ACM.

关键词： Self-supervised learning

来源：评论

学校读者我要写书评

暂无评论

PM2.5 prediction model based on multivariate feature and frequency information enhancement 4

PM2.5 prediction model based on multivariate feature and fre...

引用

4th International Conference on Electronic Information Engineering and computer Communication, EIECC 2024

作者： Yuan, Jiajing Liu, Lizhi Wuhan Institute of Technology Hubei Key Laboratory of Intelligent Robot Wuhan430205 China Wuhan Institute of Technology School of Computer Science & Engineering Artificial Intelligence Wuhan430205 China

ISBN: (纸本)9798331534622

In order to improve the prediction accuracy of PM2.5, a combined prediction model based on empirical mode decomposition, temporal convolutional network and frequency-enhanced gated attention was proposed. The eigenmode function of PM2.5 time series is obtained by empirical mode decomposition, and the sample entropy is calculated to distinguish the components of high-frequency, medium-frequency and low-frequency components. The component components are fed into the temporal convolutional network together with other relevant meteorological data to capture the local characteristics and long-term dependencies of the time series. The discrete cosine transform is used to convert the time-domain features extracted by the temporal convolutional network into the frequency domain, and the importance of different frequency components is dynamically evaluated through the attention mechanism. The experimental results show that the EMD-TCN-FEGA combined model is superior to the traditional model in PM2.5 concentration prediction, and has higher accuracy and generalization ability. © 2024 IEEE.

关键词： Empirical mode decomposition

来源：评论

学校读者我要写书评

暂无评论

Aligned Objective for Soft-Pseudo-Label Generation in Supervised Learning 41

Aligned Objective for Soft-Pseudo-Label Generation in Superv...

引用

41st International Conference on Machine Learning, ICML 2024

作者： Xu, Ning Hu, Yihao Qiao, Congyu Geng, Xin School of Computer Science and Engineering Southeast University Nanjing China Key Laboratory of New Generation Artificial Intelligence Technology and Its Interdisciplinary Applications Southeast University Ministry of Education China

Soft pseudo-labels, generated by the softmax predictions of the trained networks, offer a probabilistic rather than binary form, and have been shown to improve the performance of deep neural networks in supervised learning. Most previous methods adopt classification loss to train a classifier as the soft-pseudo-label generator and fail to fully exploit their potential due to the misalignment with the target of soft-pseudo-label generation, aimed at capturing the knowledge in the data rather than making definitive classifications. Nevertheless, manually designing an effective objective function for a soft-pseudo-label generator is challenging, primarily because datasets typically lack ground-truth soft labels, complicating the evaluation of the soft pseudo-label accuracy. To deal with this problem, we propose a novel framework that alternately trains the predictive model and the soft-pseudo-label generator guided by a meta-network-parameterized label enhancement objective. The parameters of the objective function are optimized based on the feedback from both the performance of the predictive model and the soft-pseudo-label generator in the learning task. Additionally, the framework offers versatility across different learning tasks by allowing direct modifications to the task loss. Experiments on the benchmark datasets validate the effectiveness of the proposed framework. Source code is available at https://***/palm-ml/SEAL. Copyright 2024 by the author(s)

关键词： Self-supervised learning

来源：评论

学校读者我要写书评

暂无评论

Nanoprinted high-neuron-density optical linear perceptrons performing near-infrared inference on a CMOS chip

引用

Light(science & Applications) 2021年第3期10卷 409-419页

作者： Elena Goi Xi Chen Qiming Zhang Benjamin P.Cumming Steffen schoenhardt Haitao Luan Min Gu Centre for Artificial-Intelligence Nanophotonics School of Optical-Electrical and Computer EngineeringUniversity of Shanghai for Science and TechnologyShanghai 200093China Laboratory for Artificial-Intelligence Nanophotonics School of ScienceRMIT UniversityMelbourneVIC 3001Australia

Optical machine learning has emerged as an important research area that,by leveraging the advantages inherent to optical signals,such as parallelism and high speed,paves the way for a future where optical hardware can process data at the speed of *** this work,we present such optical devices for data processing in the form of single-layer nanoscale holographic perceptrons trained to perform optical inference *** experimentally show the functionality of these passive optical devices in the example of decryptors trained to perform optical inference of single or whole classes of keys through symmetric and asymmetric *** decryptors,designed for operation in the near-infrared region,are nanoprinted on complementary metal-oxide-semiconductor chips by galvo-dithered two-photon nanolithography with axial nanostepping of 10 nm achieving a neuron density of>500 million neurons per square *** power-efficient commixture of machine learning and on-chip integration may have a transformative impact on optical decryption3,sensing4,medical diagnostics5 and computing6,7.

关键词： holographic complementary optical

来源：评论

学校读者我要写书评

暂无评论

A Provable Decision Rule for Out-of-Distribution Detection 41

A Provable Decision Rule for Out-of-Distribution Detection

引用

41st International Conference on Machine Learning, ICML 2024

作者： Ma, Xinsong Zou, Xin Liu, Weiwei School of Computer Science National Engineering Research Center for Multimedia Software Institute of Artificial Intelligence Hubei Key Laboratory of Multimedia and Network Communication Engineering Wuhan University Wuhan China

Out-of-distribution (OOD) detection task plays the key role in reliable and safety-critical applications. Existing researches mainly devote to designing or training the powerful score function but overlook investigating the decision rule based on the proposed score function. Different from previous work, this paper aims to design a decision rule with rigorous theoretical guarantee and well empirical performance. Specifically, we provide a new insight for the OOD detection task from a hypothesis testing perspective and propose a novel generalized Benjamini Hochberg (g-BH) procedure with empirical p-values to solve the testing problem. Theoretically, the g-BH procedure controls false discovery rate (FDR) at pre-specified level. Furthermore, we derive an upper bound of the expectation of false positive rate (FPR) for the g-BH procedure based on the tailed generalized Gaussian distribution family, indicating that the FPR of g-BH procedure converges to zero in probability. Finally, the extensive experimental results verify the superiority of g-BH procedure over the traditional threshold-based decision rule on several OOD detection benchmarks. Copyright 2024 by the author(s)

关键词：

来源：评论

学校读者我要写书评

暂无评论

Red Alarm for Pre-trained Models:Universal Vulnerability to Neuron-level Backdoor Attacks

引用

Machine intelligence Research 2023年第2期20卷 180-193页

作者： Zhengyan Zhang Guangxuan Xiao Yongwei Li Tian Lv Fanchao Qi Zhiyuan Liu Yasheng Wang Xin Jiang Maosong Sun Department of Computer Science and Technology Tsinghua UniversityBeijing 100084China Institute for Artificial Intelligence Tsinghua UniversityBeijing 100084China Beijing National Research Center for Information Science and Technology Beijing 100084China Huawei Noah′s Ark Laboratory Hong Kong 999077China

The pre-training-then-fine-tuning paradigm has been widely used in deep *** to the huge computation cost for pre-training,practitioners usually download pre-trained models from the Internet and fine-tune them on downstream datasets,while the downloaded models may suffer backdoor *** from previous attacks aiming at a target task,we show that a backdoored pre-trained model can behave maliciously in various downstream tasks without foreknowing task *** can restrict the output representations(the values of output neurons)of trigger-embedded samples to arbitrary predefined values through additional training,namely neuron-level backdoor attack(NeuBA).Since fine-tuning has little effect on model parameters,the fine-tuned model will retain the backdoor functionality and predict a specific label for the samples embedded with the same *** provoke multiple labels in a specific task,attackers can introduce several triggers with predefined contrastive *** the experiments of both natural language processing(NLP)and computer vision(CV),we show that NeuBA can well control the predictions for trigger-embedded instances with different trigger *** findings sound a red alarm for the wide use of pre-trained ***,we apply several defense methods to NeuBA and find that model pruning is a promising technique to resist NeuBA by omitting backdoored neurons.

关键词： Pre-trained language models backdoor attacks transformers natural language processing(NLP) computer vision(CV)

来源：评论

学校读者我要写书评

暂无评论

MIM-HD: Making Smaller Masked Autoencoder Better with Efficient Distillation 27

MIM-HD: Making Smaller Masked Autoencoder Better with Effici...

引用

27th European Conference on artificial intelligence, ECAI 2024

作者： Zhang, Zherui Wang, Changwei Xu, Rongtao Xu, Wenhao Xu, Shibiao Guo, Li Zhang, Jiguang Teng, Xiaoqiang Xu, Wenbo Artificial Intelligence Beijing University of Posts and Telecommunications China China Institute of Automation Chinese Academy of Sciences China Shandong Provincial Key Laboratory of Computer Networks Shandong Fundamental Research Center for Computer Science China

ISBN: (纸本)9781643685489

Self-supervised learning and knowledge distillation intersect to achieve exceptional performance on downstream tasks across diverse network capacities. This paper introduces MIM-HD, which implements enhancements for masked image modeling (MIM) distillation, in two key aspects. First, a vision transformer head-level relation adaptive distillation approach is proposed, allowing the student to dynamically draw multi-source knowledge from the teacher based on its evolving state, compatible with scenarios where teacher-student transformer block head count differs. Second, to address the overemphasis on the encoder and neglect of the decoder role in maintaining representation consistency in previous MIM distillations, a dual-view decoding strategy for latent visual representations is introduced, reusing the teacher's decoder to alleviate MIM burdens on smaller networks. MIM-HD effectiveness is demonstrated through evaluations on ADE20K (mIoU) and ImageNet-1K (Acc), achieving +1.4% and +0.5% improved performance, respectively, compared to state-of-the-art methods, with substantial advantages on smaller pretraining datasets. Moreover, MIM-HD achieves superior efficiency, reducing pre-training epochs from 300 to 100. © 2024 The Authors.

关键词： Decoding

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：