检索结果-内蒙古大学图书馆

International Conference on Computer Vision (ICCV)

作者： Chengxin Liu Hao Lu Zhiguo Cao Tongliang Liu Key Laboratory of Image Processing and Intelligent Control Ministry of Education School of Artificial Intelligence and Automation Huazhong University of Science and Technology China The University of Sydney Australia

We show that crowd counting can be viewed as a decomposable point querying process. This formulation enables arbitrary points as input and jointly reasons whether the points are crowd and where they locate. The querying processing, however, raises an underlying problem on the number of necessary querying points. Too few imply underestimation; too many increase computational overhead. To address this dilemma, we introduce a decomposable structure, i.e., the point-query quadtree, and propose a new counting model, termed Point quEry Transformer (PET). PET implements decomposable point querying via data-dependent quadtree splitting, where each querying point could split into four new points when necessary, thus enabling dynamic processing of sparse and dense regions. Such a querying process yields an intuitive, universal modeling of crowd as both the input and output are interpretable and steerable. We demonstrate the applications of PET on a number of crowd-related tasks, including fully-supervised crowd counting and localization, partial annotation learning, and point annotation refinement, and also report state-of-the-art performance. For the first time, we show that a single counting model can address multiple crowd-related tasks across different learning paradigms. Code is available at https://***/cxliu0/PET.

关键词：

来源：评论

学校读者我要写书评

暂无评论

An Improved Reinforcement Learning for Security-Constrained Economic Dispatch of Battery Energy Storage in Microgrids 1

引用

2nd International Conference on Neural Computing for Advanced Applications, NCAA 2021

作者： Zha, Zhongyi Wang, Bo Fan, Huijin Liu, Lei Key Laboratory of Ministry of Education for Image Processing and Intelligent Control Artificial Intelligence and Automation School Huazhong University of Science and Technology Wuhan430074 China

ISBN: (数字)9789811651885

ISBN: (纸本)9789811651878

Battery energy storage systems are widely used in microgrids integrated with volatile energy resources for their ability in peak load shifting. Security constrained economic dispatch over the system’s lifecycle is a constrained multi-period stochastic optimization problem, which is intractable. We propose an improved actor-critic-based reinforcement learning combined with a protection layer security control method for this issue, where the distributional critic net is applied to estimate the expected total reward value of a period more accurately, and the policy net with a mask action layer is used to make secure and real-time decision. Additionally, we propose a protection layer to assist the policy net as a secondary control to prevent the unsafe state of microgrids due to the trial-and-error learning of reinforcement learning. Numerical test results show the proposed algorithm can perform better than the conventional economic dispatch and other reinforcement learning algorithms while guaranteeing safe operation. © 2021, Springer Nature Singapore Pte Ltd.

关键词： Renewable energy resources

来源：评论

学校读者我要写书评

暂无评论

Complementary Learning Subnetworks for Parameter-Efficient Class-Incremental Learning

arXiv

引用

arXiv 2023年

作者： Li, Depeng Zeng, Zhigang The School of Artificial Intelligence and Automation The Institute of Artificial Intelligence Huazhong University of Science and Technology China The Key Laboratory of Image Processing and Intelligent Control of Education Ministry of China Wuhan430074 China

In the scenario of class-incremental learning (CIL), deep neural networks have to adapt their model parameters to non-stationary data distributions, e.g., the emergence of new classes over time. However, CIL models are challenged by the well-known catastrophic forgetting phenomenon. Typical methods such as rehearsal-based ones rely on storing exemplars of old classes to mitigate catastrophic forgetting, which limits real-world applications considering memory resources and privacy issues. In this paper, we propose a novel rehearsal-free CIL approach that learns continually via the synergy between two Complementary Learning Subnetworks. Our approach involves jointly optimizing a plastic CNN feature extractor and an analytical feed-forward classifier. The inaccessibility of historical data is tackled by holistically controlling the parameters of a well-trained model, ensuring that the decision boundary learned fits new classes while retaining recognition of previously learned classes. Specifically, the trainable CNN feature extractor provides task-dependent knowledge separately without interference;and the final classifier integrates task-specific knowledge incrementally for decision-making without forgetting. In each CIL session, it accommodates new tasks by attaching a tiny set of declarative parameters to its backbone, in which only one matrix per task or one vector per class is kept for knowledge retention. Extensive experiments on a variety of task sequences show that our method achieves competitive results against state-of-the-art methods, especially in accuracy gain, memory cost, training efficiency, and task-order robustness. Furthermore, to make the non-growing backbone (i.e., a model with limited network capacity) suffice to train on more incoming tasks, a graceful forgetting implementation on previously learned trivial tasks is empirically investigated. Copyright © 2023, The Authors. All rights reserved.

关键词： Decision making

来源：评论

学校读者我要写书评

暂无评论

Saliency Regularization for Self-Training with Partial Annotations

Saliency Regularization for Self-Training with Partial Annot...

引用

International Conference on Computer Vision (ICCV)

作者： Shouwen Wang Qian Wan Xiang Xiang Zhigang Zeng School of Artificial Intelligence and Automation Huazhong University of Science and Technology Key Laboratory of Image Processing and Intelligent Control Ministry of Education Wuhan Research Institute of Posts and Telecommunications

Partially annotated images are easy to obtain in multi-label classification. However, unknown labels in partially annotated images exacerbate the positive-negative imbalance inherent in multi-label classification, which affects supervised learning of known labels. Most current methods require sufficient image annotations, and do not focus on the imbalance of the labels in the supervised training phase. In this paper, we propose saliency regularization (SR) for a novel self-training framework. In particular, we model saliency on the class-specific maps, and strengthen the saliency of object regions corresponding to the present labels. Besides, we introduce consistency regularization to mine unlabeled information to complement unknown labels with the help of SR. It is verified to alleviate the negative dominance caused by the imbalance, and achieve state-of-the-art performance on Pascal VOC 2007, MS-COCO, VG-200, and Openimages V3.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Solving Nonlinear Equations Systems with a Two-Phase Root-Finder Based on Niching Differential Evolution 15th

Solving Nonlinear Equations Systems with a Two-Phase Root-Fi...

引用

15th International Conference on Bio-Inspired Computing: Theories and Applications, BIC-TA 2020

作者： Duan, Lianlang Xu, Fei Key Laboratory of Image Processing and Intelligent Control of Education Ministry of China School of Artificial Intelligence and Automation Huazhong University of Science and Technology Wuhan430074 China

ISBN: (纸本)9789811613531

Solving nonlinear equation systems (NESs) is a challenging problems in numerical computation. Two goals should be considered for solving NESs. One is to locate as many roots as possible and the other is to improve the solving precision. In this work, in order to achieve these two goals, a two-phase niching differential evolution (TPNDE) is proposed. The innovation of TPNDE is mainly reflected in the following three aspects. First, a probabilistic mutation mechanism is designed to increase the diversity of the population. Second, a novel reinitialization procedure is proposed to detect converged individuals and explore more new regions that may contain global optima. Third, distribution adjustment local search (DALS) is proposed to deal with the isolated solution and enhance the convergence of the algorithm. To evaluate the performance of TPNDE, we test our TPNDE and 5 state-of-the-art algorithms on 20 NESs with diverse features. The experimental results show that the proposed TPNDE algorithm is better than the other methods. © 2021, Springer Nature Singapore Pte Ltd.

关键词： Nonlinear equations

来源：评论

学校读者我要写书评

暂无评论

Multiobjective Brainstorm Optimization with Diversity Preservation Mechanism for Nonlinear Equation Systems 15th

Multiobjective Brainstorm Optimization with Diversity Preser...

引用

15th International Conference on Bio-Inspired Computing: Theories and Applications, BIC-TA 2020

作者： Zhao, Yi Zhu, Zelin Key Laboratory of Image Processing and Intelligent Control of Education Ministry of China School of Artificial Intelligence and Automation Huazhong University of Science and Technology Wuhan430074 China

ISBN: (纸本)9789811613531

In many fields of engineering and science, it is necessary to solve nonlinear equation systems (NESs). When using multiobjective optimization to solve NESs, there are two problems: 1) how to transform an NES into a multiobjective optimization problem and 2) how to design an algorithm to solve the transformed problems. In this work, we propose a multilayer bi-objective transformation technique, which can transform an NES into a bi-objective optimization problem, and it overcomes the curse of dimensionality and the problem of missing roots caused by the decrease of solutions discernibility in previous transformation techniques. Then, combining the multilayer bi-objective transformation technique, we design a multiobjective brainstorm optimization with a diversity preservation mechanism, which can effectively locate multiple roots of NESs in a single run. Compared with several state-of-art methods on 30 NESs with different features, our approach provides very competitive performance with the highest root ratio and success ratio. © 2021, Springer Nature Singapore Pte Ltd.

关键词： Multiobjective optimization

来源：评论

学校读者我要写书评

暂无评论

Spatial Distillation based Distribution Alignment (SDDA) for Cross-Headset EEG Classification

arXiv

引用

arXiv 2025年

作者： Liu, Dingkun Li, Siyang Wang, Ziwei Li, Wei Wu, Dongrui Ministry of Education Key Laboratory of Image Processing and Intelligent Control School of Artificial Intelligence and Automation Huazhong University of Science and Technology Wuhan430074 China Shenzhen Huazhong University of Science and Technology Research Institute Shenzhen518000 China

A non-invasive brain-computer interface (BCI) enables direct interaction between the user and external devices, typically via electroencephalogram (EEG) signals. However, decoding EEG signals across different headsets remains a significant challenge due to differences in the number and locations of the electrodes. To address this challenge, we propose a spatial distillation based distribution alignment (SDDA) approach for heterogeneous cross-headset transfer in non-invasive BCIs. SDDA uses first spatial distillation to make use of the full set of electrodes, and then input/feature/output space distribution alignments to cope with the significant differences between the source and target domains. To our knowledge, this is the first work to use knowledge distillation in cross-headset transfers. Extensive experiments on six EEG datasets from two BCI paradigms demonstrated that SDDA achieved superior performance in both offline unsupervised domain adaptation and online supervised domain adaptation scenarios, consistently outperforming 10 classical and state-of-the-art transfer learning algorithms. Copyright © 2025, The Authors. All rights reserved.

关键词： Transfer learning

来源：评论

学校读者我要写书评

暂无评论

Multimodal Brain-Computer Interfaces: AI-powered Decoding Methodologies

arXiv

引用

arXiv 2025年

作者： Li, Siyang Wang, Hongbin Chen, Xiaoqing Wu, Dongrui The Ministry of Education Key Laboratory of Image Processing and Intelligent Control School of Artificial Intelligence and Automation Huazhong University of Science and Technology Wuhan430074 China The Henan Key Laboratory of Brain Science and Brain Computer Interface Technology School of Electrical and Information Engineering Zhengzhou University China

Brain-computer interfaces (BCIs) enable direct communication between the brain and external devices. This review highlights the core decoding algorithms that enable multimodal BCIs, including a dissection of the elements, a unified view of diversified approaches, and a comprehensive analysis of the present state of the field. We emphasize algorithmic advancements in cross-modality mapping, sequential modeling, besides classic multi-modality fusion, illustrating how these novel AI approaches enhance decoding of brain data. The current literature of BCI applications on visual, speech, and affective decoding are comprehensively explored. Looking forward, we draw attention on the impact of emerging architectures like multimodal Transformers, and discuss challenges such as brain data heterogeneity and common errors. This review also serves as a bridge in this interdisciplinary field for experts with neuroscience background and experts that study AI, aiming to provide a comprehensive understanding for AI-powered multimodal BCIs. © 2025, CC BY-NC-ND.

关键词： Brain computer interface

来源：评论

学校读者我要写书评

暂无评论

Generation Maintenance Scheduling for Power Systems Considering the Risk Quantification of Hybrid Uncertainty

引用

IEEE Transactions on Power Systems 2025年

作者： Yang, Xiao Zhao, Yong Li, Yuanzheng Huang, Cheng Ding, Qiang Key Laboratory of Image Information Processing and Intelligent Control of Ministry of Education of China Huazhong University of Science and Technology School of Artificial Intelligence and Automation Wuhan430074 China Power Science Research Institute of State Grid Jiangsu Electric Power Company China China Electric Power Research Institute Company China

The accurate quantification of risk caused by uncertainty forms a crucial foundation for formulating the generation maintenance scheduling (GMS) of power systems. However, the probability distribution functions (PDFs) of uncertain variables such as wind power and load are challenging to model accurately or are unknown, which makes it difficult to measure their economic risk and formulate appropriate GMS for power systems. To address this issue, we consider hybrid uncertainty from wind power and load, and propose a novel interval-probabilistic worst conditional value-at-risk (IP-WCVaR)-based generation maintenance scheduling method. Firstly, a novel IP-WCVaR method is proposed to measure the risk of the interval and probabilistic hybrid uncertainty, and the analytical mathematical model of the IP-WCVaR is derived through typical scenarios of probability correction. On this basis, the positive and negative spinning reserve models are established using the IP-WCVaR and then integrated into the GMS model, which enhances the resilience of the power system. Finally, the new risk-averse GMS model is formulated as the lower and upper boundary optimal models, which are transformed into tractable mixed integer linear programming problems based on the interval extreme value theory. The effectiveness and superiority of the proposed IP-WCVaR method are verified on the modified IEEE 24-bus and IEEE 118-bus power systems. © 1969-2012 IEEE.

关键词： Mixed-integer linear programming

来源：评论

学校读者我要写书评

暂无评论

A novel method of constructing high-dimensional digital chaotic systems on finite-state automata

引用

Chinese Physics B 2020年第9期29卷 233-243页

作者： Jun Zheng Han-Ping Hu School of Artificial Intelligence and Automation Huazhong University of Science and TechnologyWuhan 430074China Key Laboratory of Image Information Processing and Intelligent Control Ministry of EducationWuhan 430074China

When chaotic systems are implemented on finite precision machines, it will lead to the problem of dynamical degradation. Aiming at this problem, most previous related works have been proposed to improve the dynamical degradation of low-dimensional chaotic maps. This paper presents a novel method to construct high-dimensional digital chaotic systems in the domain of finite computing precision. The model is proposed by coupling a high-dimensional digital system with a continuous chaotic system. A rigorous proof is given that the controlled digital system is chaotic in the sense of Devaney's definition of chaos. Numerical experimental results for different high-dimensional digital systems indicate that the proposed method can overcome the degradation problem and construct high-dimensional digital chaos with complicated dynamical properties. Based on the construction method, a kind of pseudorandom number generator (PRNG) is also proposed as an application.

关键词： high-dimensional digital chaotic system dynamical degradation anti-control pseudorandom number generator

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：