检索结果-内蒙古大学图书馆

21st OITS International Conference on Information Technology, OCIT 2023

作者： Patel, Ruchi Verma, Ashok Kumar Kshirsagar, Ravindra V. Sahu, Neelesh Kumar Gyan Ganga Institute of Technology and Sciences Department of Computer Science and Engineering MP Jabalpur India Gyan Ganga Institute of Technology and Sciences Department of Electronics and Communication MP Jabalpur India Gyan Ganga Institute of Technology and Sciences Department of Artificial Intelligence and Robotics MP Jabalpur India

ISBN: (纸本)9798350358230

Memory and other mental processes are both severely disrupted by Alzheimer's disease (AD), a neurodegenerative condition. It interferes with almost every cognitive process that the brain is capable of. This ultimately results in a smaller and less volumetric brain as time passes. There is currently no treatment that can reverse the effects of Alzheimer's disease. The only way for early detection and therapy to be possible is for the symptoms to be recognized promptly. Throughout the years, there has been a significant amount of research conducted on the application of machine learning to the diagnosis and classification of Alzheimer's disease. The performance of linear, polynomial, and RBF (Radial Basis Function) classification kernels in the context of AD classification using the Support Vector Machine (SVM) with the Principal Component Architecture (PCA) is investigated in this study. As a result, a framework is provided for the categorization of AD, which is comprised of the following steps: data input, model building, hyperparameter tuning, prediction on test data, performance evaluation, and selection of the most effective SVM kernel model and PCA for dimension reduction. ADNI and the Alzheimer's MRI Preprocessed dataset that is available on Kaggle are used to conduct an evaluation of the proposed framework. The performance of the model is evaluated using accuracy measure for both the datasets. Across both datasets, the SVM linear kernel with PCA achieved the maximum accuracy, which was 99.99 percent. © 2023 IEEE.

关键词： Support vector machines

来源：评论

学校读者我要写书评

暂无评论

W2SAT: Learning to generate SAT instances from Weighted Literal Incidence Graphs

arXiv

引用

arXiv 2023年

作者： Wen, Weihuang Yu, Tianshu The Chinese University of Hong Kong Shenzhen China Shenzhen Institute of Artificial Intelligence and Robotics for Society China

The Boolean Satisfiability (SAT) problem stands out as an attractive NP-complete problem in theoretic computer science and plays a central role in a broad spectrum of computing-related applications. Exploiting and tuning SAT solvers under numerous scenarios require massive high-quality industry-level SAT instances, which unfortunately are quite limited in the real world. To address the data insufficiency issue, in this paper, we propose W2SAT, a framework to generate SAT formulas by learning intrinsic structures and properties from given real-world/industrial instances in an implicit fashion. To this end, we introduce a novel SAT representation called Weighted Literal Incidence Graph (WLIG), which exhibits strong representation ability and generalizability against existing counterparts, and can be efficiently generated via a specialized learning-based graph generative model. Decoding from WLIGs into SAT problems is then modeled as finding overlapping cliques with a novel hill-climbing optimization method termed Optimal Weight Coverage (OWC). Experiments demonstrate the superiority of our WLIG-induced approach in terms of graph metrics, efficiency, and scalability in comparison to previous methods. Additionally, we discuss the limitations of graph-based SAT generation for real-world applications, especially when utilizing generated instances for SAT solver parameter-tuning, and pose some potential directions. © 2023, CC BY.

关键词： Computational complexity

来源：评论

学校读者我要写书评

暂无评论

Pseudo Labels Refinement with Intra-Camera Similarity for Unsupervised Person Re-Identification

Pseudo Labels Refinement with Intra-Camera Similarity for Un...

引用

IEEE International Conference on Image Processing

作者： Pengna Li Kangyi Wu Sanping Zhou Qianxin Huang Jinjun Wang Xi’an Jiaotong University Institute of Artificial Intelligence and Robotics Xi’an P. R. China

Unsupervised person re-identification (Re-ID) aims to retrieve person images across cameras without any identity labels. Most clustering-based methods roughly divide image features into clusters and neglect the feature distribution noise caused by domain shifts among different cameras, leading to inevitable performance degradation. To address this challenge, we propose a novel label refinement framework with clustering intra-camera similarity. Intra-camera feature distribution pays more attention to the appearance of pedestrians and labels are more reliable. We conduct intra-camera training to get local clusters in each camera, respectively, and refine inter-camera clusters with local results. We hence train the Re-ID model with refined reliable pseudo labels in a self-paced way. Extensive experiments demonstrate that the proposed method surpasses state-of-the-art performance. Code is available at https://***/leeBooMla/ICSR.

关键词：

来源：评论

学校读者我要写书评

暂无评论

OmniMamba: Efficient and Unified Multimodal Understanding and Generation via State Space Models

arXiv

引用

arXiv 2025年

作者： Zou, Jialv Liao, Bencheng Zhang, Qian Liu, Wenyu Wang, Xinggang School of EIC Huazhong University of Science & Technology China Institute of Artificial Intelligence Huazhong University of Science & Technology China Horizon Robotics China

Recent advancements in unified multimodal understanding and visual generation (or multimodal generation) models have been hindered by their quadratic computational complexity and dependence on large-scale training data. We present OmniMamba, the first linear-architecture-based multimodal generation model that generates both text and images through a unified next-token prediction paradigm. The model fully leverages Mamba-2’s high computational and memory efficiency, extending its capabilities from text generation to multimodal generation. To address the data inefficiency of existing unified models, we propose two key innovations: (1) decoupled vocabularies to guide modality-specific generation, and (2) task-specific LoRA for parameter-efficient adaptation. Furthermore, we introduce a decoupled two-stage training strategy to mitigate data imbalance between two tasks. Equipped with these techniques, OmniMamba achieves competitive performance with JanusFlow while surpassing Show-o across benchmarks, despite being trained on merely 2M image-text pairs, which is 1,000 times fewer than Show-o. Notably, OmniMamba stands out with outstanding inference efficiency, achieving up to a 119.2× speedup and 63% GPU memory reduction for long-sequence generation compared to Transformer-based counterparts. Code and models are released at https://***/hustvl/ OmniMamba Copyright © 2025, The Authors. All rights reserved.

关键词： State space methods

来源：评论

学校读者我要写书评

暂无评论

Group UAV Navigation by Qualifying Human-Machine Decisions in Hybrid Reinforcement Learning

Group UAV Navigation by Qualifying Human-Machine Decisions i...

引用

Chinese Automation Congress (CAC)

作者： Xuyang Li Jianwu Fang Kai Du Jianru Xue Chang'an University Xi'an China Institute of Artificial Intelligence and Robotics Xi'an Jiaotong University Xi'an China

In this paper, we focus on the continuous control of Unmanned Aerial Vehicle (UAV) group in large-scale 3D complex environment based on deep reinforcement learning (DRL) method. The purpose is to make the UAV group safely reach the random target area from a certain starting point, and the flight height and speed are variable during the navigation process. In this paper, a DRL framework combining the human-in-the-loop method is designed. The UAV group is preformed into a mobile whole, and the sensor data of the UAV group is directly mapped to the control signal. The role of human-in-the-loop is to switch the human-machine control right if necessary, so that humans can intervene and correct the dangerous actions of the agent. Based on this framework, an improved Actor-Critic structure is designed, and the policy and value network of the original structure are modified accordingly. We verify the success rate and time efficiency of different numbers of UAV group navigation in the urban environment. The experimental results show that this method can reduce the training convergence time and improve the efficiency and success rate of navigation.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Coordinated Restoration of Generators and Load for the High Renewable Energy Penetrated Power System with Frequency Regulation 7

Coordinated Restoration of Generators and Load for the High ...

引用

7th IEEE Conference on Energy Internet and Energy System Integration, EI2 2023

作者： Yang, Chao Liao, Huanxin Wang, Shuyi Bai, Yan Li, Shaoyan Zhao, Junhua School of Science and Engineering The Chinese University of Hong Kong Shenzhen Shenzhen China Shenzhen Institute of Artificial Intelligence and Robotics For Society Shenzhen China School of Electrical and Electronic Engineering North China Electric Power University Baoding China

ISBN: (纸本)9798350345094

The frequency dynamic of converter-based renewable energy generators is much different from the traditional inertia-based generators in the restoration process of the high renewable energy penetrated power system (HREPPS). Considering the frequency regulation capability (FRC) of renewable generators, this paper proposes an optimization method of coordinating generator restoration with load restoration in the network configuration stage of the HREPPS. Firstly, the unified transfer function structure is introduced to analyze the FRC of restored HREPPSs. Then a quantification model of the maximum pick-up load is proposed considering the frequency dynamic performance of restored HREPPSs. Secondly, the optimization model with FRC is proposed to coordinated restore all generators and more load in the shortest time. Finally, results on a modified IEEE 39-bus system are studied to verify the applicability of the proposed FRC model and coordinated restoration method for the HREPPS. This work can serve as an important guidance for operators to develop restoration strategies for the blackout HREPPS. © 2023 IEEE.

关键词： Restoration

来源：评论

学校读者我要写书评

暂无评论

OmniRL: In-Context Reinforcement Learning by Large-Scale Meta-Training in Randomized Worlds

arXiv

引用

arXiv 2025年

作者： Wang, Fan Shao, Pengtao Zhang, Yiming Yu, Bo Liu, Shaoshan Ding, Ning Cao, Yang Kang, Yu Wang, Haifeng Shenzhen Institute of Artificial Intelligence and Robotics for Society Shenzhen China University of Science and Technology of China Shenzhen China Baidu Inc Beijing China

We introduce OmniRL 1, a highly generalizable in-context reinforcement learning (ICRL) model that is meta-trained on hundreds of thousands of diverse tasks. These tasks are procedurally generated by randomizing state transitions and rewards within Markov Decision Processes 2. To facilitate this extensive meta-training, we propose two key innovations: (1) An efficient data synthesis pipeline for ICRL, which leverages the interaction histories of diverse behavior policies;and (2) A novel modeling framework that integrates both imitation learning and reinforcement learning (RL) within the context, by incorporating prior knowledge. For the first time, we demonstrate that in-context learning (ICL) alone, without any gradient-based fine-tuning, can successfully tackle unseen Gymnasium tasks through imitation learning, online RL, or offline RL. Additionally, we show that achieving generalized ICRL capabilities—unlike task identification-oriented few-shot learning—critically depends on long trajectories generated by variant tasks and diverse behavior policies. By emphasizing the potential of ICL and departing from pre-training focused on acquiring specific skills, we further underscore the significance of meta-training aimed at cultivating the ability of ICL itself. © 2025, CC BY.

关键词： Reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

Learning to Decouple Complex Systems

arXiv

引用

arXiv 2023年

作者： Zhou, Zihan Yu, Tianshu The Chinese University of Hong Kong Shenzhen China Shenzhen Institute of Artificial Intelligence and Robotics for Society China

A complex system with cluttered observations may be a coupled mixture of multiple simple subsystems corresponding to latent entities. Such sub-systems may hold distinct dynamics in the continuous-time domain;therein, complicated interactions between sub-systems also evolve over time. This setting is fairly common in the real world but has been less considered. In this paper, we propose a sequential learning approach under this setting by decoupling a complex system for handling irregularly sampled and cluttered sequential observations. Such decoupling brings about not only subsystems describing the dynamics of each latent entity but also a meta-system capturing the interaction between entities over time. Specifically, we argue that the meta-system evolving within a simplex is governed by projected differential equations (ProjDEs). We further analyze and provide neural-friendly projection operators in the context of Bregman divergence. Experimental results on synthetic and real-world datasets show the advantages of our approach when facing complex and cluttered sequential data compared to the state-of-the-art. © 2023, CC BY.

关键词： Continuous time systems

来源：评论

学校读者我要写书评

暂无评论

MAS-SAM: Segment Any Marine Animal with Aggregated Features

arXiv

引用

arXiv 2024年

作者： Yan, Tianyu Wan, Zifu Deng, Xinhao Zhang, Pingping Liu, Yang Lu, Huchuan School of Future Technology School of Artificial Intelligence Dalian University of Technology China Robotics Institute Carnegie Mellon University United States

Recently, Segment Anything Model (SAM) shows exceptional performance in generating high-quality object masks and achieving zero-shot image segmentation. However, as a versatile vision model, SAM is primarily trained with large-scale natural light images. In underwater scenes, it exhibits substantial performance degradation due to the light scattering and absorption. Meanwhile, the simplicity of the SAM’s decoder might lead to the loss of fine-grained object details. To address the above issues, we propose a novel feature learning framework named MAS-SAM for marine animal segmentation, which involves integrating effective adapters into the SAM’s encoder and constructing a pyramidal decoder. More specifically, we first build a new SAM’s encoder with effective adapters for underwater scenes. Then, we introduce a Hypermap Extraction Module (HEM) to generate multi-scale features for a comprehensive guidance. Finally, we propose a Progressive Prediction Decoder (PPD) to aggregate the multi-scale features and predict the final segmentation results. When grafting with the Fusion Attention Module (FAM), our method enables to extract richer marine information from global contextual cues to fine-grained local details. Extensive experiments on four public MAS datasets demonstrate that our MAS-SAM can obtain better results than other typical segmentation methods. The source code is available at https://***/Drchip61/MAS-SAM. Copyright © 2024, The Authors. All rights reserved.

关键词： Decoding

来源：评论

学校读者我要写书评

暂无评论

Refiner: Fine-grained Cross-modal Concepts Refinement for Compositional Zero-Shot Learning

Refiner: Fine-grained Cross-modal Concepts Refinement for Co...

引用

International Conference on Acoustics, Speech, and Signal Processing (ICASSP)

作者： Xiao Zhang Haodong Jing Hui Chen Yongqiang Ma Nanning Zheng National Key Laboratory of Human-Machine Hybrid Augmented Intelligence National Engineering Research Center for Visual Information and Applications and Institute of Artificial Intelligence and Robotics Xi’an Jiaotong University China

ISBN: (数字)9798350368741

ISBN: (纸本)9798350368758

Recent Compositional Zero-Shot Learning (CZSL) methods increasingly adopt the pre-trained vision-language models to capture the contextual relations between image and text spaces. However, the single-class-token design from Transformer-based encoder inevitably captures contextual information from unrelated objects and background, thus hindering the modeling of fine-grained class-specific visual features. Suffering from cross-modal gap, prior methods also struggle to improve compositional recognition performance. To address these issues, we propose a fine-grained cross-modal concepts refinement framework, termed as Refiner, which comprises two pivotal components: (i) the fine-grained concepts refinement of image embeddings to capture state-object context within visual scenes, and (ii) the cross-modal information fusion to mitigate the modality gap. By leveraging learnable query vectors to capture region-specific semantic information pertinent to composition labels, our approach refines visual representations with fine-grained state-object context information. As for cross-modal information fusion, we construct a robust image-to-text mapping by aligning visual embeddings with states, objects, and compositions, respectively. Extensive experiments demonstrate that our Refiner achieves new state-of-the-art performance across all popular benchmarks in both closed- and open-world settings.

关键词： Visualization Zero shot learning Semantics Benchmark testing Signal processing Transformers Vectors Acoustics Speech processing Context modeling

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：