检索结果-内蒙古大学图书馆

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

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

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

AWeCita:Generating Answer with Appropriate and Well-grained Citations Using LLMs

引用

Data intelligence 2024年第4期6卷 1134-1157页

作者： Suifeng Zhao Tong Zhou Zhuoran Jin Hongbang Yuan Yubo Chen Kang Liu Sujian Li International School Beijing University of Posts and TelecommunicationsBeijing100876China The Laboratory of Cognition and Decision Intelligence for Complex Systems Institute of AutomationChinese Academy of SciencesBeijing 100190China School of Artificial Intelligence University of Chinese Academy of SciencesBeijing 100190China School of Computer Science Peking UniversityBeijing 100871China

Large language models(LLMs)excel in various Natural Language Processing tasks but struggle with hallucinations,leading to potentially misleading *** have extensively explored LLMs'citation ***,existing efforts often overlook the crucial aspects of the appropriateness and granularity of citation,which are vital for mitigating hallucination and enhancing *** bridge this gap and improve the quality of citations,we propose the Generating Answers with Appropriate and Well-grained Citations using LLMs task(AWeCita),with a focus on citing appropriately with a well *** on the traditional evaluation metrics of answer accuracy and citation correctness,we introduce two new evaluation metrics,citation appropriateness and citation granularity,to assess LLMs'performance on this task more comprehensively and *** conduct a series of exploratory experiments on ASQA and ELI5 *** experimental results show that,AWeCita outperforms traditional tasks in the metric of citation granularity,most of our methods show a certain advantage incitation appropriateness,however,the improvement towards well-grained citation affects the quote-level citation correctness.

关键词： Question answering Large language models Citation Citation appropriateness Citation granularity

来源：评论

学校读者我要写书评

暂无评论

RamSeg: Real-time Multimodal Semantic Segmentation for Autonomous SLAM Systems

RamSeg: Real-time Multimodal Semantic Segmentation for Auton...

引用

2024 IEEE International Conference on Unmanned Systems, ICUS 2024

作者： He, Yong Chen, Chi Hu, Zongtian Xu, Yuhang Sun, Shangzhe Jin, Ang Li, Liuchun Yang, Bisheng State Key Laboratory of Information Engineering in Surveying Mapping and Remote Sensing Wuhan University Wuhan China Institute of Artificial Intelligence School of Computer Science Wuhan University Wuhan China

ISBN: (纸本)9798350384185

Semantic segmentation significantly enhances the capabilities of autonomous SLAM systems. We proposed RamSeg, a multimodal 3D semantic segmentation approach for autonomous SLAM systems, supporting the real-time transmission and storage of segmentation results with localization information. The camera images and LiDAR point clouds are acquired simultaneously, then image segmentation is performed. In the point to image projection module, the points within the camera's view frustum are projected onto the image segmentation mask and the corresponding label is assigned to the point to obtain 3D segmentation result. Ultimately, the 3D semantic segmentation map of the entire scene is obtained by merging the data from each moment utilizing SLAM. The experiment was carried out around the Star Lake Building on Wuhan University using the Luo-Jia Explorer system. The experimental results indicate that the approach can reach a maximum inference speed of 14Hz with RTX 4070 graphic card while the data captured by the system is 10Hz, meeting the real-time requirement while having excellent segmentation result in indoor and outdoor scenes. © 2024 IEEE.

关键词： Semantic Segmentation

来源：评论

学校读者我要写书评

暂无评论

Cubature Kalman Fusion Filtering Under Amplify-and-Forward Relays With Randomly Varying Channel Parameters

引用

IEEE/CAA Journal of Automatica Sinica 2025年第2期12卷 356-368页

作者： Jiaxing Li Zidong Wang Jun Hu Hongli Dong Hongjian Liu the Department of Applied Mathematics Harbin University of Science and Technology IEEE the Department of Computer Science Brunel University London the School of Automation Harbin University of Science and Technology the Artificial Intelligence Energy Research Institute Northeast Petroleum University the Heilongjiang Provincial Key Laboratory of Networking and Intelligent Control Northeast Petroleum University the National Key Laboratory of Continental Shale Oil of China Northeast Petroleum University the Key Laboratory of Advanced Perception and Intelligent Control of High-End Equipment Ministry of Education Anhui Polytechnic University the School of Mathematics and Physics Anhui Polytechnic University

In this paper, the problem of cubature Kalman fusion filtering(CKFF) is addressed for multi-sensor systems under amplify-and-forward(AaF) relays. For the purpose of facilitating data transmission, AaF relays are utilized to regulate signal communication between sensors and filters. Here, the randomly varying channel parameters are represented by a set of stochastic variables whose occurring probabilities are permitted to exhibit bounded uncertainty. Employing the spherical-radial cubature principle, a local filter under AaF relays is initially constructed. This construction ensures and minimizes an upper bound of the filtering error covariance by designing an appropriate filter gain. Subsequently, the local filters are fused through the application of the covariance intersection fusion rule. Furthermore, the uniform boundedness of the filtering error covariance's upper bound is investigated through establishing certain sufficient conditions. The effectiveness of the proposed CKFF scheme is ultimately validated via a simulation experiment concentrating on a three-phase induction machine.

关键词： Amplify-and-forward (AaF) relays covariance intersection fusion cubature Kalman filtering multi-sensor systems uniform boundedness

来源：评论

学校读者我要写书评

暂无评论

Cloth-aware Augmentation for Cloth-generalized Person Re-identification 24

Cloth-aware Augmentation for Cloth-generalized Person Re-ide...

引用

32nd ACM International Conference on Multimedia, MM 2024

作者： Liu, Fangyi Ye, Mang Du, Bo National Engineering Research Center for Multimedia Software Institute of Artificial Intelligence School of Computer Science Hubei Key Laboratory of Multimedia and Network Communication Engineering Wuhan University Wuhan China

ISBN: (纸本)9798400706868

Person re-identification (ReID) is crucial in video surveillance, aiming to match individuals across different camera views while cloth-changing person re-identification (CC-ReID) focuses on pedestrians changing attire. Many existing CC-ReID methods overlook generalization, crucial for universality across cloth-consistent and cloth-changing scenarios. This paper pioneers exploring the cloth-generalized person re-identification (CG-ReID) task and introduces the Cloth-aware Augmentation (CaAug) strategy. Comprising domain augmentation and feature augmentation, CaAug aims to learn identity-relevant features adaptable to both scenarios. Domain augmentation involves creating diverse fictitious domains and simulating various clothing scenarios. Supervising features from different cloth domains enhances robustness and generalization against clothing changes. Additionally, for feature augmentation, element exchange introduces diversity concerning clothing changes. Regularizing the model with these augmented features strengthens resilience against clothing change uncertainty. Extensive experiments on cloth-changing datasets demonstrate the efficacy of our approach, consistently outperforming state-of-the-art methods. © 2024 ACM.

关键词： Feature extraction

来源：评论

学校读者我要写书评

暂无评论

A Theoretical Analysis of Backdoor Poisoning Attacks in Convolutional Neural Networks 41

A Theoretical Analysis of Backdoor Poisoning Attacks in Conv...

引用

41st International Conference on Machine Learning, ICML 2024

作者： Li, Boqi 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

The rising threat of backdoor poisoning attacks (BPAs) on Deep Neural Networks (DNNs) has become a significant concern in recent years. In such attacks, the adversaries strategically target a specific class and generate a poisoned training set. The neural network (NN), well-trained on the poisoned training set, is able to predict any input with the trigger pattern as the targeted label, while maintaining accurate outputs for clean inputs. However, why the BPAs work remains less explored. To fill this gap, we employ a dirty-label attack and conduct a detailed analysis of BPAs in a two-layer convolutional neural network. We provide theoretical insights and results on the effectiveness of BPAs. Our experimental results on two real-world datasets validate our theoretical findings. Copyright 2024 by the author(s)

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Virtual Image Generation: Bridging Reality and Virtuality for Long-Tail Traffic scenes 4

Virtual Image Generation: Bridging Reality and Virtuality fo...

引用

4th IEEE International Conference on Digital Twins and Parallel intelligence, DTPI 2024

作者： Xu, Feibing Zhang, Hui Suo, Xiaohua Li, Yidong Beijing Jiaotong University Ministry of Education Key Laboratory of Big Data & Artificial Intelligence in Transportation China Beijing Jiaotong University School of Computer Science and Technology Beijing100044 China

ISBN: (纸本)9798350349252

Although visual perception algorithms have made significant progress in most normal scenes, it is still challenging for autonomous driving systems to accurately perceive long-tail scenes that occur less frequently, which can lead to serious traffic safety issues. However, existing open-source datasets do not systematically collect sufficient long-tail scenes. To fill this gap, we propose a pipeline for designing large-scale, diverse long-tail traffic scenes and generating virtual datasets based on the parallel vision approach. A virtual dataset named Vir-LTTS (virtual long-tail traffic scenes) is built, comprising various scenes such as extreme weather conditions, adverse lighting conditions, traffic accidents, unique forms of traffic objects, and blurry images caused by camera defects. We investigate the potential of training models using the Vir-LTTS dataset in long-tail traffic scenes. Experimental results show that pre-training with Vir-LTTS significantly improves the performance of visual models in long-tail traffic scenes. © 2024 IEEE.

关键词： Virtual environments

来源：评论

学校读者我要写书评

暂无评论

DCARE: Decentralized Collaborative Autonomous Robotic Exploration

DCARE: Decentralized Collaborative Autonomous Robotic Explor...

引用

2024 IEEE International Conference on Unmanned Systems, ICUS 2024

作者： Zhao, Leyi Chen, Chi Sun, Shangzhe Li, Liuchun Jin, Ang Hu, Zongtian Xu, Yuhang Yang, Bisheng State Key Laboratory of Information Engineering in Surveying Mapping and Remote Sensing Wuhan University Wuhan China Institute of Artificial Intelligence School of Computer Science Wuhan University Wuhan China

ISBN: (纸本)9798350384185

Autonomous exploration of complex unknown environment challenges the intelligent perception and navigation abilities of unmanned system. Traditional single-robot method suffers from low efficiency and low risk resistance capacity. This paper introduces a decentralized multi-robot autonomous exploration system DCARE that can collaboratively explore complex environment with LiDAR. On the single-robot layer, we develop a frontier-based exploration strategy with deciding exploration goal based on information gain, then a probabilistic-based controller is utilized to navigate the robot. On the multi-robot layer, robots share and incrementally merge perceived map and states, thus robots cooperate based on the combined information. We have conducted experiment in a maze with random pillars and walls, the proposed method finishes the exploration in 383s with 95% spatial coverage rate, achieves 72% improvement in exploration efficiency. © 2024 IEEE.

关键词： Decentralized systems

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：