检索结果-内蒙古大学图书馆

Region-adaptive Concept Aggregation for Few-shot Visual Recognition

Machine Intelligence Research 2023年第4期20卷 554-568页

作者： Mengya Han Yibing Zhan Baosheng Yu Yong Luo Han Hu Bo Du Yonggang Wen Dacheng Tao School of Computer Science National Engineering Research Center for Multimedia SoftwareWuhan UniversityWuhan430072China Hubei Luojia Laboratory Wuhan430072China School of Computer Science The University of SydneySydney2006Australia JD Explore Academy Beijing101116China School of Information and Electronics Beijing Institute of TechnologyBeijing100081China School of Computer Science and Engineering Nanyang Technological UniversitySingapore639798Singapore

Few-shot learning (FSL) aims to learn novel concepts from very limited examples. However, most FSL methods suffer from the issue of lacking robustness in concept learning. Specifically, existing FSL methods usually ignore the diversity of region contents that may contain concept-irrelevant information such as the background, which would introduce bias/noise and degrade the performance of conceptual representation learning. To address the above-mentioned issue, we propose a novel metric-based FSL method termed region-adaptive concept aggregation network or RCA-Net. Specifically, we devise a region-adaptive concept aggregator (RCA) to model the relationships of different regions and capture the conceptual information in different regions, which are then integrated in a weighted average manner to obtain the conceptual representation. Consequently, robust concept learning can be achieved by focusing more on the concept-relevant information and less on the conceptual-irrelevant information. We perform extensive experiments on three popular visual recognition benchmarks to demonstrate the superiority of RCA-Net for robust few-shot learning. In particular, on the Caltech-UCSD Birds-200-2011 (CUB200) dataset, the proposed RCA-Net significantly improves 1-shot accuracy from 74.76% to 78.03% and 5-shot accuracy from 86.84% to 89.83% compared with the most competitive counterpart.

关键词： Few-shot learning metric-based meta learning concept learning region-adaptive concept-aggregation

来源：评论

学校读者我要写书评

暂无评论

Online Sexism Detection and Classification by Injecting User Gender Information

Online Sexism Detection and Classification by Injecting User...

引用

2023 IEEE International Conference on Artificial Intelligence, Blockchain, and Internet of Things, AIBThings 2023

作者： Das, Amit Rahgouy, Mostafa Zhang, Zheng Bhattacharya, Tathagata Dozier, Gerry Seals, Cheryl D. Auburn University Department of Computer Science and Software Engineering AuburnAL United States Auburn University at Montgomery Department of Computer Science MontgomeryAL United States

ISBN: (纸本)9798350322347

This paper investigates the potential effects that user gender information has on online sexism detection, in terms of both binary and multi class detection. Social media has recently developed into a center for sexist posts that target especially women. Since most sexist comments are made especially against people of a particular gender, whether the gender information of the users could be effective or not for sexism detection, is still an important question. Here we try to address this issue using Natural Language Processing (NLP) and machine learning models. Experiments showed that combining user gender information with textual features improved classification performance both in terms of binary classification and multi class classification. The effectiveness of the proposed strategy is demonstrated by the experimental results reported in this research. © 2023 IEEE.

关键词： Classification (of information)

来源：评论

学校读者我要写书评

暂无评论

A survey on model-based reinforcement learning

引用

science China(Information sciences) 2024年第2期67卷 59-84页

作者： Fan-Ming LUO Tian XU Hang LAI Xiong-Hui CHEN Weinan ZHANG Yang YU National Key Laboratory for Novel Software Technology Nanjing University Polixir. ai Department of Computer Science and Engineering Shanghai Jiao Tong University

Reinforcement learning(RL) interacts with the environment to solve sequential decision-making problems via a trial-and-error approach. Errors are always undesirable in real-world applications, even though RL excels at playing complex video games that permit several trial-and-error attempts. To improve sample efficiency and thus reduce errors, model-based reinforcement learning(MBRL) is believed to be a promising direction, as it constructs environment models in which trial-and-errors can occur without incurring actual costs. In this survey, we investigate MBRL with a particular focus on the recent advancements in deep RL. There is a generalization error between the learned model of a non-tabular environment and the actual environment. Consequently, it is crucial to analyze the disparity between policy training in the environment model and that in the actual environment, guiding algorithm design for improved model learning, model utilization, and policy training. In addition, we discuss the recent developments of model-based techniques in other forms of RL, such as offline RL, goal-conditioned RL, multi-agent RL, and meta-RL. Furthermore,we discuss the applicability and benefits of MBRL for real-world tasks. Finally, this survey concludes with a discussion of the promising future development prospects for MBRL. We believe that MBRL has great unrealized potential and benefits in real-world applications, and we hope this survey will encourage additional research on MBRL.

关键词： reinforcement learning model-based reinforcement learning planning model learning model learning with reduced error model usage

来源：评论

学校读者我要写书评

暂无评论

Exploring the Predictive Capabilities of AlphaFold Using Adversarial Protein Sequences

IEEE Transactions on Artificial Intelligence

引用

IEEE Transactions on Artificial Intelligence 2024年第7期5卷 3384-3392页

作者： Alkhouri, Ismail R. Jha, Sumit Beckus, Andre Atia, George Jha, Susmit Ewetz, Rickard Velasquez, Alvaro OrlandoFL32816 United States Michigan State University Computational Mathematics Science and Engineering Department East LansingMI48824 United States University of Michigan Electrical Engineering and Computer Science Department Ann ArborMI48109 United States Florida International University Knights Foundation School of Computing and Information Sciences MiamiFL33199 United States Air Force Research Laboratory Rome Information Directorate NY13441 United States Department Computer Science Department OrlandoFL32816 United States SRI International Computer Science Laboratory Menlo ParkCA94025 United States Electrical and Computer Engineering Department OrlandoFL32816 United States University of Colorado Computer Science Department BoulderCO80309 United States

Protein folding neural networks (PFNNs) such as AlphaFold predict remarkably accurate structures of proteins compared to other approaches. However, the robustness of such networks has heretofore not been fully explored. This is particularly relevant given the broad social implications of such technologies and the fact that biologically small perturbations to noncritical residues of a protein sequence do not typically lead to drastic changes in the protein structure. Our study demonstrates that, similar to adversarial methods in machine learning, small changes to protein sequences can result in significant differences in the predicted protein structures using AlphaFold as determined by large distance measures. Despite this, our findings using multiple protein sequences suggest that AlphaFold is able to accurately predict the domain structure and folding regions of a protein. To gauge structural differences, we employ two alignment-based measures [root-mean-square deviation (RMSD) and the global distance test (GDT) similarity], and one alignment-free measure, which is an effective graph-based structure representation (GraSR) method. We prove that the problem of minimally perturbing protein sequences is NP-complete. Based on the well-established block substitution matrices (BLOSUM62) sequence alignment scoring matrix, we generate adversarial sequences. In our experimental evaluation, we consider 111 proteins (including 29 COVID-19 sequences) in the Universal Protein resource (UniProt), a central resource for protein data. Our findings suggest that, despite the high RMSD values returned by AlphaFold, it is capable of handling the BLOSUM adversarial sequences considered in our analysis, as evidenced by the preservation of the folded regions and the GraSR results. © 2020 IEEE.

关键词： Neural networks

来源：评论

学校读者我要写书评

暂无评论

Business Scenario Driven Reinforcement Learning Testing Method 26

Business Scenario Driven Reinforcement Learning Testing Meth...

引用

26th ACIS International Winter Conference on software engineering, Artificial Intelligence, Networking and Parallel/Distributed Computing, SNPD-Winter 2023

作者： Cai, Lizhi Wang, Jin School of Information Science and Engineering East China University of Science and Technology Shanghai Key Laboratory of Computer Software Testing and Evaluating Shanghai China

ISBN: (纸本)9798350345865

Reinforcement learning has been successfully applied in software testing, but the existing testing methods cannot perform effective testing according to the characteristics of applications, and using outdated interactive experience during training, resulting in inefficient testing. In this paper, we propose BSDRTesting. Firstly, the demonstration experience of human users is collected according to the functional scenarios and business logic of each application, and combining reinforcement learning and imitation learning to maximize rewards while imitating user behavior, experience replay aims to sample experiences from the agent's self-exploration and expert demonstrations to improve sampling efficiency. At the same time, according to the input rules, the black-box testing method is used to fully test the input events, and finally an experience filtering mechanism is proposed, and the reward value and TD-Error are used as the basis for priority sampling. The experimental results on 10 open source applications show BSDRTesting has achieved significant improvements in code coverage and branch coverage compared with existing methods. © 2023 IEEE.

关键词： Reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

Competition for roadside camera monocular 3D object detection

引用

National science Review 2023年第6期10卷 34-37页

作者： Jinrang Jia Yifeng Shi Yuli Qu Rui Wang Xing Xu Hai Zhang Baidu Inc. Institute of Artificial Intelligence and Robotics Xi'an Jiaotong University College of Software Jilin University School of Computer Science and Engineering University of Electronic Science and Technology of China Pazhou Laboratory (Huangpu) School of Mathematics Northwest University

INTRODUCTION Accurate environment perception is a critical topic in autonomous driving and intelligent *** environmental perception methods mostly rely on on-board ***,limited by the installation height,thereare problems such as blind spots and unstable long-range perception in vehicle perceptual ***,with the rapid improvement of intelligent infrastructure,it has become possible to use roadside cameras for traffic environment *** from the increased height when compared with on-boardsensors,roadside cameras can obtain a larger perceptual field of view and realize long-range observation.

关键词：

来源：评论

学校读者我要写书评

暂无评论

A Secure and Efficient Framework for Multi-Round Data Trading Over the Internet of Artificially Intelligent Things

引用

IEEE Internet of Things Magazine 2022年第1期5卷 119-124页

作者： Zheng, Xu Zhang, Lizong Hui, Bei Tian, Ling Cai, Zhipeng School of Computer Science and Engineering University of Electronic Science and Technology of China China School of Information and Software Engineering University of Electronic Science and Technology of China China Georgia State University Department of Computer Science United States

IoT data trading has greatly benefited the popularization of both the Internet of Things (IoT) and Artificial Intelligence of Things (AIoT). Current solutions mainly treat the dataset owned by each device as a commodity and focus on maintaining a data market. Meanwhile, inspired by recent achievements in distributed machine learning and federated learning, AIoT can actually realize its services by retaining the data locally on devices and only exchanging model parameters. However, existing IoT data trading methods fail to meet this secure and efficient process. Therefore, this article proposes a novel framework for data trading over AIoT. It allows the service provider to trade on deep learning model training instead of purchasing the full datasets. Key factors for the security issues and data pricing are addressed for the framework, including the design of the learning parameters and the comprehensive privacy concerns. Then a novel data trading strategy is proposed for the service provider to jointly maintain the model performance and the budget consumption. Evaluation results reveal the improvements on the model performance. Finally, some open problems in the design of data trading in AIoTs are discussed. © 2018 IEEE.

关键词： Internet of things

来源：评论

学校读者我要写书评

暂无评论

USee: Ultrasound-based Device-free Eye Movement Sensing 21

USee: Ultrasound-based Device-free Eye Movement Sensing

引用

21st Annual IEEE International Conference on Sensing, Communication, and Networking, SECON 2024

作者： Cheng, Wen Pang, Mingzhi Wan, Haoran Dong, Shichen Liu, Dongxu Wang, Wei State Key Laboratory for Novel Software Technology Nanjing University Nanjing China Department of Computer Science Princeton University Princeton United States

ISBN: (纸本)9798331519186

Eye movements play a significant role in human-computer interaction and are widely recognized as an essential health indicator, making their detection both appealing and technically challenging. In this paper, we present a system named USEE that achieves high-precision capture of weak and aperiodic eye movements by utilizing fine-grained and ubiquitous ultrasound signals, capturing both blinking and more subtle saccades. We first identify signal changes associated with eye movements by capturing the unique impact of blinking. Further, we establish a pioneering relationship between the residuals from signal decomposition and subtle eye movements. Utilizing innovative signal processing architectures, we mitigate interference and effectively extract eye movement features. Subsequently, we employ one-dimensional convolutional operations in place of signal cross-correlation, designing filters for motion category identification and a lightweight convolutional neural network for saccade direction classification. This enables our system to serve as a foundational sensing layer for eye movement tracking, applicable across diverse applications. We implement USEE on both a research-purpose platform and a commodity Raspberry Pi. Extensive experimental results demonstrate the effectiveness of our system, achieving 91% accuracy in saccade recognition and 94% in blink detection. The system proves robust, even in challenging scenarios with strong interference, such as the presence of moving pedestrians. © 2024 IEEE.

关键词： Motion sensors

来源：评论

学校读者我要写书评

暂无评论

LAMB: Label-Induced Mixed-Level Blending for Multimodal Multi-label Emotion Detection 19th

LAMB: Label-Induced Mixed-Level Blending for Multimodal Mul...

引用

19th EAI International Conference on Collaborative Computing: Networking, Applications and Worksharing, CollaborateCom 2023

作者： Qian, Shuwei Guo, Ming Fan, Zhicheng Chen, Mingcai Wang, Chongjun State Key Laboratory for Novel Software Technology Nanjing University Nanjing China Department of Computer Science and Technology Nanjing University Nanjing China

ISBN: (纸本)9783031545276

To better understand complex human emotions, there is growing interest in utilizing heterogeneous sensory data to detect multiple co-occurring emotions. However, existing studies have focused on extracting static information from each modality, while overlooking various interactions within and between modalities. Additionally, the label-to-modality and label-to-label dependencies still lack exploration. In this paper, we propose LAbel-induced Mixed-level Blending (LAMB) to address these challenges. Mixed-level blending leverages shallow but manifold self-attention and cross-attention encoders in parallel to model unimodal context dependency and cross-modal interaction simultaneously. This is in contrast to previous works either use one of them or cascade them successively, which ignores the diversity of interaction in multimodal data. LAMB also employs label-induced aggregation to allow different labels to attend to the most relevant blended tokens adaptively using a transformer-based decoder, which facilitates the exploration of label-to-modality dependency. Unlike common low-order strategies in multi-label learning, correlations among multiple labels can be learned by self-attention in label embedding space before being treated as queries. Comprehensive experiments demonstrate the effectiveness of our methods for multimodal multi-label emotion detection. © ICST Institute for computer sciences, Social Informatics and Telecommunications engineering 2024.

关键词： Emotion Recognition

来源：评论

学校读者我要写书评

暂无评论

An Efficient Character-Level Adversarial Attack Inspired by Textual Variations in Online Social Media Platforms

引用

computer Systems science & engineering 2023年第12期47卷 2869-2894页

作者： Jebran Khan Kashif Ahmad Kyung-Ah Sohn Department of Artificial Intelligence Ajou UniversitySuwonKorea Department of Computer Science Munster Technological UniversityCorkIreland Department of Software and Computer Engineering Ajou UniversitySuwonKorea

In recent years,the growing popularity of social media platforms has led to several interesting natural language processing(NLP)***,these social media-based NLP applications are subject to different types of adversarial attacks due to the vulnerabilities of machine learning(ML)and NLP *** work presents a new low-level adversarial attack recipe inspired by textual variations in online social media *** variations are generated to convey the message using out-of-vocabulary words based on visual and phonetic similarities of characters and words in the shortest possible *** intuition of the proposed scheme is to generate adversarial examples influenced by human cognition in text generation on social media platforms while preserving human robustness in text understanding with the fewest possible *** intentional textual variations introduced by users in online communication motivate us to replicate such trends in attacking text to see the effects of such widely used textual variations on the deep learning *** this work,the four most commonly used textual variations are chosen to generate adversarial ***,this article introduced a word importance ranking-based beam search algorithm as a searching method for the best possible perturbation *** effectiveness of the proposed adversarial attacks has been demonstrated on four benchmark datasets in an extensive experimental setup.

关键词： Adversarial attack text classification social media character-level attack phonetic similarity visual similarity word importance rank beam search

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：