检索结果-内蒙古大学图书馆

arXiv 2021年

作者： Geng, Binzong Yang, Min Yuan, Fajie Wang, Shupeng Ao, Xiang Xu, Ruifeng University of Science and Technology of China China Shenzhen Institutes of Advanced Technology Chinese Academy of Sciences Westlake University Key Lab of Intelligent Information Processing Chinese Academy of Sciences Institute of Computing Technology CAS Harbin Institute of Technology Shenzhen China Tencent

Lifelong learning capabilities are crucial for sentiment classifiers to process continuous streams of opinioned information on the Web. However, performing lifelong learning is non-trivial for deep neural networks as continually training of incrementally availab.e information inevitably results in catastrophic forgetting or interference. In this paper, we propose a novel iterative network pruning with uncertainty regularization method for lifelong sentiment classification (IPRLS), which leverages the principles of network pruning and weight regularization. By performing network pruning with uncertainty regularization in an iterative manner, IPRLS can adapt a single BERT model to work with continuously arriving data from multiple domains while avoiding catastrophic forgetting and interference. Specifically, we leverage an iterative pruning method to remove redundant parameters in large deep networks so that the freed-up space can then be employed to learn new tasks, tackling the catastrophic forgetting problem. Instead of keeping the old-tasks fixed when learning new tasks, we also use an uncertainty regularization based on the Bayesian online learning framework to constrain the update of old tasks weights in BERT, which enables positive backward transfer, i.e. learning new tasks improves performance on past tasks while protecting old knowledge from being lost. In addition, we propose a task-specific low-dimensional residual function in parallel to each layer of BERT, which makes IPRLS less prone to losing the knowledge saved in the base BERT network when learning a new task. Extensive experiments on 16 popular review corpora demonstrate that the proposed IPRLS method significantly outperforms the strong baselines for lifelong sentiment classification. For reproducibility, we submit the code and data at: https://***/siat-nlp/IPRLS. Copyright © 2021, The Authors. All rights reserved.

关键词： Deep neural networks

来源：评论

学校读者我要写书评

暂无评论

Global-Local Attention Network for Semantic Segmentation in Aerial Images

Global-Local Attention Network for Semantic Segmentation in ...

引用

International Conference on Pattern Recognition

作者： Minglong Li Lianlei Shan Xiaobin Li Yang Bai Dengji Zhou Weiqiang Wang Ke Lv Bin Luo Si-Bao Chen University of Chinese Academy of Sciences Beijing China Aerospace Information Research Institute Chinese Academy of Science Beijing China MOE Key Lab of Signal Processing and Intelligent Computing School of Computer Science and Technology Anhui University Hefei China

Errors in semantic segmentation could be classified into two types: the large area misclassification and inaccurate local boundaries. Previously attention-based methods typically capture rich global contextual information, which benefits the large area classification but cannot address the local errors of boundaries. In this paper, we propose a Global-Local Attention Network (GLANet) which can simultaneously consider the global context and local details. Specifically, our GLANet consists of two branches: (1) the global attention branch and (2) local attention branch. Furthermore, three different modules are embedded in GLANet for respectively modelling the semantic interdependencies in spatial, channel and boundary dimension. Lastly, we merge the outputs of different branches to enhance the feature representation further, resulting in more precise segmentation. Overall, the proposed method achieves the competitive segmentation accuracy on two public aerial image datasets, bringing significant improvements over the existing baselines.

关键词： Image segmentation Image color analysis Image edge detection Semantics Vegetation mapping Vegetation Pattern recognition

来源：评论

学校读者我要写书评

暂无评论

Overview of the Tenth Dialog System Technology Challenge: DSTC10

引用

IEEE/ACM Transactions on Audio Speech and Language processing 2024年 32卷 765-778页

作者： Yoshino, Koichiro Chen, Yun-Nung Crook, Paul Kottur, Satwik Li, Jinchao Hedayatnia, Behnam Moon, Seungwhan Fei, Zhengcong Li, Zekang Zhang, Jinchao Feng, Yang Zhou, Jie Kim, Seokhwan Liu, Yang Jin, Di Papangelis, Alexandros Gopalakrishnan, Karthik Hakkani-Tur, Dilek Damavandi, Babak Geramifard, Alborz Hori, Chiori Shah, Ankit Zhang, Chen Li, Haizhou Sedoc, Joao D'haro, Luis F. Banchs, Rafael Rudnicky, Alexander Guardian Robot Project R-IH RIKEN 2-2-2 Hikaridai Seika Shoraku619-0288 Japan Information Science Nara Institute of Science and Technology Ikoma630-0101 Japan Computer Science and Information Engineering National Taiwan University Taipei10617 Taiwan Inc. Palo AltoCA95054 United States Alexa AI *** Inc. SunnyvaleCA94089 United States Meta Seattle RedmondWA98052 United States Institute of Computing Technology Chinese Academy of Sciences Beijing100190 China Key Laboratory of Intelligent Information Processing Institute of Computing Technology Chinese Academy of Sciences Beijing100190 China Tencent AI Lab Beijing Beijing China Kexueyuan South Road Zhongguancun Beijing100190 China Beijing 100190 China Alexa AI *** Inc. SunnyvaleCA United States 1120 Enterprise way Sunnyvale94089 United States *** Inc. SeattleWA United States Menlo Park CA United States Audio and Speech Group Mitsubishi Electric Research Laboratories CambridgeMA02139-1955 United States Carnegie Mellon University Department of Language and Information Technologies or just Carnegie Mellon University Pittsburgh United States National University of Singapore Singapore Singapore Department of Electrical and Computer Engineering National University of Singapore Singapore Singapore Shenzhen Research Institute of Big Data School of Data Science Chinese University of Hong Kong Shenzhen518172 China New York University New YorkNY United States ETSI de Telecomunicacion - Speech Technology and Machine Learning Group Universidad Politecnica de Madrid Ciudad Universitaria Madrid28040 Spain Nanyang Technological University Singapore Singapore Carnegie Mellon University PittsburghPA United States

This article introduces the Tenth Dialog System Technology Challenge (DSTC-10). This edition of the DSTC focuses on applying end-to-end dialog technologies for five distinct tasks in dialog systems, namely 1. Incorporation of Meme images into open domain dialogs, 2. Knowledge-grounded Task-oriented Dialogue Modeling on Spoken Conversations, 3. Situated Interactive Multimodal dialogs, 4. Reasoning for Audio Visual Scene-Aware Dialog, and 5. Automatic Evaluation and Moderation of Open-domainDialogue Systems. This article describes the task definition, provided datasets, baselines, and evaluation setup for each track. We also summarize the results of the submitted systems to highlight the general trends of the state-of-the-art technologies for the tasks. © 2023 The Authors.

关键词： Job analysis

来源：评论

学校读者我要写书评

暂无评论

A Review of Artificial Fish Swarm Algorithms: Recent Advances and Applications

arXiv

引用

arXiv 2020年

作者： Pourpanah, Farhad Wang, Ran Lim, Chee Peng Wang, Xi-Zhao Yazdani, Danial College of Mathematics and Statistics Guangdong Key Lab. of Intelligent Information Processing Shenzhen University China Department of Electrical and Computer Engineering University of Windsor Canada College of Mathematics and Statistics Shenzhen Key Lab. of Advanced Machine Learning and Applications Guangdong Key Lab. of Intelligent Information Processing Shenzhen University China Institute for Intelligent Systems Research and Innovation Deakin University Australia College of Computer Science and Software Engineering Guangdong Key Lab. of Intelligent Information Processing Shenzhen University China School of Computer Science and Engineering Southern University of Science and Technology China

The Artificial Fish Swarm Algorithm (AFSA) is inspired by the ecological behaviors of fish schooling in nature, viz., the preying, swarming and following behaviors. Owing to a number of salient properties, which include flexibility, fast convergence, and insensitivity to the initial parameter settings, the family of AFSA has emerged as an effective Swarm Intelligence (SI) methodology that has been widely applied to solve real-world optimization problems. Since its introduction in 2002, many improved and hybrid AFSA models have been developed to tackle continuous, binary, and combinatorial optimization problems. This paper aims to present a concise review of the continuous AFSA, encompassing the original ASFA, its improvements and hybrid models, as well as their associated applications. We focus on articles published in high-quality journals since 2013. Our review provides insights into AFSA parameters modifications, procedure and sub-functions. The main reasons for these enhancements and the comparison results with other hybrid methods are discussed. In addition, hybrid, multi-objective and dynamic AFSA models that have been proposed to solve continuous optimization problems are elucidated. We also analyse possible AFSA enhancements and highlight future research directions for advancing AFSA-based models. Copyright © 2020, The Authors. All rights reserved.

关键词： Multiobjective optimization

来源：评论

学校读者我要写书评

暂无评论

Design of People Flow Monitoring System in Public Place based on MD-MCNN

Design of People Flow Monitoring System in Public Place base...

引用

2020 International Conference on 5G Mobile Communication and information Science, MCIS-5G 2020

作者： Tianmin, Xiong Xiaochun, Lei Xingwen, Zheng Junyan, Chen Yizhou, Feng School of Computer and Information Security Guilin University of Electronic Technology Guilin541004 China Guangxi Colleges and Universities Key Lab. of Intelligent Processing of Computer Images and Graphics Guilin541004 China Guangxi Cooperative Innovation Center of Cloud Computing and Big Data Guilin University of Electronic Technology Guilin541004 China

Due to the limitation of hardware resources, the traditional people flow monitoring system based on computer vision in public places can't meet different crowd-scale scenarios. Therefore, a people flow monitoring system based on MD-MCNN algorithm is designed, which is an application system combining the improved SSD object detection algorithm MNSSD and MCNN density map regression algorithm. In the initial stage, the system uses MNSSD for accurate detection and counting. If the people flow gradually reaches a certain threshold, the system automatically uses MCNN to estimate people flow until the people flow falls below the threshold. Through the experimental verification, the system can realize the people flow statistics of low-density and high-density people in different scenarios, and can be applied on the existing embedded platform. This scheme can be extended to smart cities, smart scenic spots, smart transportation and other fields. © 2020 Published under licence by IOP Publishing Ltd.

关键词： Object detection

来源：评论

学校读者我要写书评

暂无评论

Design of intelligent Robot Platform based on Multi-sensor Fusion

Design of Intelligent Robot Platform based on Multi-sensor F...

引用

2020 International Conference on 5G Mobile Communication and information Science, MCIS-5G 2020

作者： Dajin, Ya Xiaochun, Lei Yue, Li Junyan, Chen Rongcun, Huang Lin, Lan School of Computer and Information Security Guilin University of Electronic Technology Guilin541004 China Guangxi Colleges and Universities Key Lab. of Intelligent Processing of Computer Images and Graphics Guilin541004 China Guangxi Cooperative Innovation Center of Cloud Computing and Big Data Guilin University of Electronic Technology Guilin541004 China

The mobile robot adapts to the more complicated indoor and outdoor environments, and can expand its scope of application. In order to reduce the influence of the cumulative error caused by navigation in complex environments, the indoor mobile robot that combines Inertial Measurement Unit (IMU) and encoder fusion is designed and implemented. In view of the limitations of the traditional single lidar scheme, a Multi-sensor Fusion scheme is proposed to achieve indoor map construction, path planning, multi-point navigation and other functions, and a MSIF KartoSLAM (Multi-sensor information Fusion) algorithm is proposed, which combines the KartoSLAM algorithm and Multi-sensor information to achieve map construction in complex environments. Through comprehensive testing in the indoor environment, the results show that the Multi-sensor Fusion scheme is superior to the traditional single lidar scheme, and can achieve higher accuracy in mapping and navigation. At the same time, the robot platform can also be combined with the Internet of Things technology and integrated into intelligent housing system. © 2020 Published under licence by IOP Publishing Ltd.

关键词： Navigation

来源：评论

学校读者我要写书评

暂无评论

Characterizing Multi-domain False News and Underlying User Effects on Chinese Weibo

arXiv

引用

arXiv 2022年

作者： Sheng, Qiang Cao, Juan Bernard, H. Russell Shu, Kai Li, Jintao Liu, Huan Key Lab of Intelligent Information Processing Institute of Computing Technology Chinese Academy of Sciences Beijing China University of Chinese Academy of Sciences Beijing China Institute for Social Science Research Arizona State University TempeAZ United States Department of Computer Science Illinois Institute of Technology ChicagoIL United States Computer Science and Engineering Arizona State University TempeAZ United States

False news that spreads on social media has proliferated over the past years and has led to multi-aspect threats in the real world. While there are studies of false news on specific domains (like politics or health care), little work is found comparing false news across domains. In this article, we investigate false news across nine domains on Weibo, the largest Twitter-like social media platform in China, from 2009 to 2019. The newly collected data comprise 44,728 posts in the nine domains, published by 40,215 users, and reposted over 3.4 million times. Based on the distributions and spreads of the multi-domain dataset, we observe that false news in domains that are close to daily life like health and medicine generated more posts but diffused less effectively than those in other domains like politics, and that political false news had the most effective capacity for diffusion. The widely diffused false news posts on Weibo were associated strongly with certain types of users - by gender, age, etc. Further, these posts provoked strong emotions in the reposts and diffused further with the active engagement of false-news starters. Our findings have the potential to help design false news detection systems in suspicious news discovery, veracity prediction, and display and explanation. The comparison of the findings on Weibo with those of existing work demonstrates nuanced patterns, suggesting the need for more research on data from diverse platforms, countries, or languages to tackle the global issue of false news. The code and new anonymized dataset are availab.e at https://***/ICTMCG/Characterizing-Weibo-Multi-Domain-False-News. © 2022, CC BY-NC-ND.

关键词： Social networking (online)

来源：评论

学校读者我要写书评

暂无评论

OpenAUC: Towards AUC-Oriented Open-Set Recognition

arXiv

引用

arXiv 2022年

作者： Wang, Zitai Xu, Qianqian Yang, Zhiyong He, Yuan Cao, Xiaochun Huang, Qingming SKLOIS Institute of Information Engineering CAS China School of Cyber Security University of Chinese Academy of Sciences China Key Lab. of Intelligent Information Processing Institute of Computing Tech. CAS China School of Computer Science and Tech. University of Chinese Academy of Sciences China Alibaba Group China School of Cyber Science and Tech. Sun Yat-sen University Shenzhen Campus China BDKM University of Chinese Academy of Sciences China Peng Cheng Laboratory China

Traditional machine learning follows a close-set assumption that the training and test set share the same lab.l space. While in many practical scenarios, it is inevitable that some test samples belong to unknown classes (open-set). To fix this issue, Open-Set Recognition (OSR), whose goal is to make correct predictions on both close-set samples and open-set samples, has attracted rising attention. In this direction, the vast majority of literature focuses on the pattern of open-set samples. However, how to evaluate model performance in this challenging task is still unsolved. In this paper, a systematic analysis reveals that most existing metrics are essentially inconsistent with the aforementioned goal of OSR: (1) For metrics extended from close-set classification, such as Open-set F-score, Youden’s index, and Normalized Accuracy, a poor open-set prediction can escape from a low performance score with a superior close-set prediction. (2) Novelty detection AUC, which measures the ranking performance between close-set and open-set samples, ignores the close-set performance. To fix these issues, we propose a novel metric named OpenAUC. Compared with existing metrics, OpenAUC enjoys a concise pairwise formulation that evaluates open-set performance and close-set performance in a coupling manner. Further analysis shows that OpenAUC is free from the aforementioned inconsistency properties. Finally, an end-to-end learning method is proposed to minimize the OpenAUC risk, and the experimental results on popular benchmark datasets speak to its effectiveness. Project Page: https://***/wang22ti/OpenAUC. © 2022, CC BY.

关键词： Forecasting

来源：评论

学校读者我要写书评

暂无评论

Adversarial Learning with Cost-Sensitive Classes

arXiv

引用

arXiv 2021年

作者： Shen, Haojing Chen, Sihong Wang, Ran Wang, Xizhao Big Data Institute College of Computer Science and Software Engineering Guangdong Key Lab. of Intelligent Information Processing Shenzhen University Guangdong Shenzhen518060 China The College of Mathematics and Statistics Shenzhen University Shenzhen518060 China The Shenzhen Key Laboratory of Advanced Machine Learning and Applications Shenzhen University Shenzhen518060 China

It is necessary to improve the performance of some special classes or to particularly protect them from attacks in adversarial learning. This paper proposes a framework combining cost-sensitive classification and adversarial learning together to train a model that can distinguish between protected and unprotected classes, such that the protected classes are less vulnerable to adversarial examples. We find in this framework an interesting phenomenon during the training of deep neural networks, called Min-Max property, that is, the absolute values of most parameters in the convolutional layer approach zero while the absolute values of a few parameters are significantly larger becoming bigger. Based on this Min-Max property which is formulated and analyzed in a view of random distribution, we further build a new defense model against adversarial examples for adversarial robustness improvement. An advantage of the built model is that it performs better than the standard one and can combine with adversarial training to achieve an improved performance. It is experimentally confirmed that, regarding the average accuracy of all classes, our model is almost as same as the existing models when an attack does not occur and is better than the existing models when an attack occurs. Specifically, regarding the accuracy of protected classes, the proposed model is much better than the existing models when an attack occurs. © 2021, CC BY.

关键词： Deep neural networks

来源：评论

学校读者我要写书评

暂无评论

Closed-Loop Safe Correction for Reinforcement Learning Policy 4th

Closed-Loop Safe Correction for Reinforcement Learning Poli...

引用

4th International Conference on Ubiquitous Security, UbiSec 2024

作者： Yi, Zhi Lv, Qi Chen, Shuhong Liang, Ying Dai, Yinglong Hunan Provincial Key Laboratory of Intelligent Computing and Language Information Processing College of Information Science and Engineering Hunan Normal University Changsha410081 China School of Computer Science and Cyber Engineering Guangzhou University Guangzhou510006 China Blockchain Innovation Lab Swinburne University of Technology MelbourneVIC3122 Australia Molecular Nutrition Branch National Engineering Research Center of Rice and By-product Deep Processing College of Food Science and Engineering Central South University of Forestry and Technology Hunan Changsha410004 China

ISBN: (纸本)9789819648351

Trial and error learning is an approach with uncertain consequences. How to maintain policy security, stability, and efficiency under controlled circumstances, posing a significant academic challenge. Such as Reinforcement Learning (RL) leverages the neural network parameter space to identify the optimal solution for achieving the optimal mapping of the policy space. However, even a slight fluctuation in the parameter space can lead to policy collapse. To solve it, we propose a method called Closed-loop Safe Correction (CLSC). This method employs twin agents to establish a closed-loop framework for policy and sampling data distribution, gradually improving policy efficiency while ensuring policy safety. Base on theoretical and experimental analysis, CLSC elucidates the performance, influencing factors, and advantages of this approach in policy safety scenarios. These findings provide novel research insights and practical directions for advancing safe RL. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： Reinforcement learning

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

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

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：