检索结果-内蒙古大学图书馆

38th Conference on Neural Information processing Systems, NeurIPS 2024

作者： Meng, Benyuan Xu, Qianqian Wang, Zitai Cao, Xiaochun Huang, Qingming 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 Technology CAS China Peng Cheng Laboratory China School of Cyber Science and Tech. Shenzhen Campus of Sun Yat-sen University China School of Computer Science and Tech. University of Chinese Academy of Sciences China Key Laboratory of Big Data Mining and Knowledge Management CAS China

Diffusion models are initially designed for image generation. Recent research shows that the internal signals within their backbones, named activations, can also serve as dense features for various discriminative tasks such as semantic segmentation. Given numerous activations, selecting a small yet effective subset poses a fundamental problem. To this end, the early study of this field performs a large-scale quantitative comparison of the discriminative ability of the activations. However, we find that many potential activations have not been evaluated, such as the queries and keys used to compute attention scores. Moreover, recent advancements in diffusion architectures bring many new activations, such as those within embedded ViT modules. Both combined, activation selection remains unresolved but overlooked. To tackle this issue, this paper takes a further step with a much broader range of activations evaluated. Considering the significant increase in activations, a full-scale quantitative comparison is no longer operational. Instead, we seek to understand the properties of these activations, such that the activations that are clearly inferior can be filtered out in advance via simple qualitative evaluation. After careful analysis, we discover three properties universal among diffusion models, enabling this study to go beyond specific models. On top of this, we present effective feature selection solutions for several popular diffusion models. Finally, the experiments across multiple discriminative tasks validate the superiority of our method over the SOTA competitors. Our code is available at this url. © 2024 Neural information processing systems foundation. All rights reserved.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Suppress Content Shift: Better Diffusion Features via Off-the-Shelf Generation Techniques 38

Suppress Content Shift: Better Diffusion Features via Off-th...

引用

38th Conference on Neural Information processing Systems, NeurIPS 2024

作者： Meng, Benyuan Xu, Qianqian Wang, Zitai Yang, Zhiyong Cao, Xiaochun Huang, Qingming 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 Technology CAS China Peng Cheng Laboratory China School of Computer Science and Tech. University of Chinese Academy of Sciences China School of Cyber Science and Tech. Shenzhen Campus of Sun Yat-sen University China Key Laboratory of Big Data Mining and Knowledge Management CAS China

Diffusion models are powerful generative models, and this capability can also be applied to discrimination. The inner activations of a pre-trained diffusion model can serve as features for discriminative tasks, namely, diffusion feature. We discover that diffusion feature has been hindered by a hidden yet universal phenomenon that we call content shift. To be specific, there are content differences between features and the input image, such as the exact shape of a certain object. We locate the cause of content shift as one inherent characteristic of diffusion models, which suggests the broad existence of this phenomenon in diffusion feature. Further empirical study also indicates that its negative impact is not negligible even when content shift is not visually perceivable. Hence, we propose to suppress content shift to enhance the overall quality of diffusion features. Specifically, content shift is related to the information drift during the process of recovering an image from the noisy input, pointing out the possibility of turning off-the-shelf generation techniques into tools for content shift suppression. We further propose a practical guideline named GATE to efficiently evaluate the potential benefit of a technique and provide an implementation of our methodology. Despite the simplicity, the proposed approach has achieved superior results on various tasks and datasets, validating its potential as a generic booster for diffusion features. Our code is available at this url. © 2024 Neural information processing systems foundation. All rights reserved.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Point Cloud Compression Method Based on Curvature Grading and Inter-point Compression for Industrial Products

Point Cloud Compression Method Based on Curvature Grading an...

引用

International Conference on Cyber-Enabled Distributed Computing and Knowledge Discovery, CyberC

作者： Lei Wang Wei Huang Yiping Chen Ran Chen School of Computer Nanjing University of Posts and Telecommunications Nanjing P. R. China Jiangsu Key Laboratory of Big Data Security and Intelligent Processing Nanjing P. R. China

The traditional point cloud compression methods fail to meet the compression requirements of complex surface point cloud files in the industrial field. This paper proposes a point cloud compression method suitable for industrial products with defective and complex surfaces, which compresses the defect and non-defect parts separately using different compression approaches. A curvature-based compression method is designed for the defect points, and an inter-point compression method is developed for the non-defect part, achieving compression of both components of the point cloud. The experimental results show the advantages of the proposed compression method through a comparative analysis of time efficiency, compression ratio, and reconstruction accuracy for industrial point cloud compression.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Path Planning based on Reinforcement Learning with Improved APF model for Synergistic Multi-UAVs

Path Planning based on Reinforcement Learning with Improved ...

引用

International Conference on Computer Supported Cooperative Work in Design

作者： Qun Ding Xiaolong Xu Wenming Gui Jiangsu Key Laboratory of Big Data Security & Intelligent Processing Nanjing China School of Computer Science Nanjing University of Posts and Telecommunications Nanjing China School of Computer Science Jinling Institute of Technology Nanjing China

As the emerging technology of Unmanned Aerial Vehicles (UAVs) becomes mature, UAVs are widely used in environmental monitoring, communication and other fields. In view of this, this paper analyzed the task of synergistic multi-UAVs exploration of unknown environments, and proposed a path planning method for them based on reinforcement learning. Firstly, the path planning task of the UAVs was divided into two parts: the path travel strategy module and the information exploration strategy module. Models of the two modules were based on the Deep Deterministic Policy Gradient algorithm (DDPG), and an improved Artificial Potential Field (APF) force traction mechanism was introduced in the path travel strategy module. Its aim was to assist in guiding the generation of UAV flight path trajectories. Also it could enhance the learning capability of the model. The path travel strategy module would generate the complete flight path of the whole cluster in a distributed manner. A series of temporary target points provided by the information exploration strategy module helped. In maps with 21.5%, 25.3% and 29.6% of obstacles, multi-UAVs could achieve 84.2%, 76.7% and 69.9% of environmental exploration by the designed method. Compared with the APF method, the A star method and the Breath First Search (BFS) method, the proposed method is not only able to plan feasible paths in a more complex map model, but also the curvature of the planned paths is smoother, thus achieving the goal of reducing the energy cost of UAVs.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Collaborative Bi-Aggregation for Directed Graph Embedding

SSRN

引用

SSRN 2023年

作者： Liu, Linsong Chen, Ke-Jia Liu, Zheng Jiangsu Key Laboratory of Big Data Security & Intelligent Processing Nanjing University of Posts and Telecommunications Jiangsu Nanjing210023 China School of Computer Science Nanjing University of Posts and Telecommunications Jiangsu Nanjing210023 China State Key Laboratory of Novel Software Technology Nanjing University Jiangsu Nanjing210093 China

Directed graph is able to model asymmetric relationships between nodes and research on directed graph embedding is of great significance in downstream graph analysis and inference. Learning source and target embeddings of nodes separately to preserve edge asymmetry has become the dominant approach, but also poses challenge for learning representations of low or even zero in/out degree nodes that are ubiquitous in sparse graphs. In this paper, a collaborative bi-directional aggregation method (COBA) for directed graph embedding is proposed. Firstly, the source and target embeddings of the central node are learned by aggregating from the counterparts of the source and target neighbors, respectively;Secondly, the source/target embeddings of the zero in/out degree central nodes are enhanced by aggregating the counterparts of opposite-directional neighbors (i.e. target/source neighbors);Finally, source and target embeddings of the same node are correlated to achieve collaborative aggregation. Both the feasibility and rationality of the model are theoretically analyzed. Extensive experiments on real-world datasets demonstrate that COBA comprehensively outperforms state-of-the-art methods on multiple tasks and meanwhile validates the effectiveness of proposed aggregation strategies. © 2023, The Authors. All rights reserved.

关键词： Directed graphs

来源：评论

学校读者我要写书评

暂无评论

SLBERT: An Improved FLAT-BERT for Named Entity Recognition

SSRN

引用

SSRN 2022年

作者： Fei, Yuefan Xu, Xiaolong Jiangsu Key Laboratory of Big Data Security & Intelligent Processing Nanjing University of Posts and Telecommunications Jiangsu Nanjing China School of Computer Science Nanjing University of Posts and Telecommunications Jiangsu Nanjing China

Named Entity Recognition (NER) aims to identify named entities mentioned in unstructured text and classify them into predefined named entity classes. Although models using word fusion have achieved relatively high performance, the recognition of ambiguous entities in text remains challenging, and the performance of the models depends on a sufficient amount of manually labeled data;exploring models that fuse more feature dimensions and schemes that fuse existing datasets is of farreaching interest. In this work, we propose an improved scheme of FLAT-BERT, SLBERT, that can be used in the field of named entity *** scheme consists of two phases that more fully exploit the global semantics of the text. In the first stage, the model is trained based on the current dataset, another dataset is predicted for cross-dataset fusion, and the correctness of label annotation is improved by entity confidence modeling. In the second stage, the global semantics of the text is extracted using Sentence BERT and embedded into the feature matrix encoded using Lattice BERT for subsequent Token classification. We have conducted experiments on several datasets, and the experimental results demonstrate the effectiveness of the proposed scheme in this paper. In terms of F1 values, compared with FLAT-BERT, the improvement is 0.15%, 0.34%, 0.61%, and 0.58% on datasets OntoNotes, MSRA, Resume, and Weibo, respectively. © 2022, The Authors. All rights reserved.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

A Point Cloud Registration Method for Substations Based on an Improved SAC-IA Algorithm

A Point Cloud Registration Method for Substations Based on a...

引用

Chinese Automation Congress (CAC)

作者： Lei Wang Yiping Chen Haonan Zong Lulu Wang Jun Yin School of Computer Nanjing University of Posts and Telecommunications Nanjing PR China Jiangsu Key Laboratory of Big Data Security and Intelligent Processing Nanjing PR China School of Internet of Things Nanjing University of Posts and Telecommunications Nanjing PR China

This paper proposes a point cloud registration method for substations based on an improved SAC-IA algorithm. This method optimizes the SAC-IA algorithm by filtering the randomly selected point pairs to ensure that the triangles formed by the selected points in the model and scene point clouds have certain similarities. Furthermore, the registration error judgment of the SAC-IA algorithm has been improved. In addition to using the Euclidean distance between the registered model and scene point clouds as the judgment standard, this method also considers the SHOT difference and average curvature difference. Successful registration is only considered when all three standards are satisfied. The experimental research shows that the time performance of this method is twice as high as that of the traditional SAC-IA algorithm on average, and the recognition accuracy is improved in the recognition results.

关键词：

来源：评论

学校读者我要写书评

暂无评论

A comprehensive survey on shadow removal from document images: datasets, methods, and opportunities

引用

Vicinagearth 2025年第1期2卷 1-18页

作者： Wang, Bingshu Li, Changping Zou, Wenbin Zhang, Yongjun Chen, Xuhang Chen, C.L. Philip School of Software Northwestern Polytechnical University Xi’an China Guangdong Provincial Key Laboratory of Intelligent Information Processing & Shenzhen Key Laboratory of Media Security Shenzhen University Shenzhen China Guangdong Key Laboratory of Intelligent Information Processing College of Electronics and Information Engineering Shenzhen University Shenzhen China Yongjun Zhang is with the State Key Laboratory of Public Big Data College of Computer Science and Technology Guizhou University Guiyang China School of Computer Science and Engineering Huizhou University Huizhou China School of Computer Science and Engineering South China University of Technology and Pazhou Lab Guangzhou China

With the rapid development of document digitization, people have become accustomed to capturing and processing documents using electronic devices such as smartphones. However, the captured document images often suffer from issues like shadows and noise due to environmental factors, which can affect their readability. To improve the quality of captured document images, researchers have proposed a series of models or frameworks and applied them in distinct scenarios such as image enhancement, and document information extraction. In this paper, we primarily focus on shadow removal methods and open-source datasets. We concentrate on recent advancements in this area, first organizing and analyzing nine available datasets. Then, the methods are categorized into conventional methods and neural network-based methods. Conventional methods use manually designed features and include shadow map-based approaches and illumination-based approaches. Neural network-based methods automatically generate features from data and are divided into single-stage approaches and multi-stage approaches. We detail representative algorithms and briefly describe some typical techniques. Finally, we analyze and discuss experimental results, identifying the limitations of datasets and methods. Future research directions are discussed, and nine suggestions for shadow removal from document images are proposed. To our knowledge, this is the first survey of shadow removal methods and related datasets from document images.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Raft Consensus Algorithm Based on Credit Model in Consortium Blockchain

引用

Wuhan University Journal of Natural Sciences 2020年第2期25卷 146-154页

作者： CHEN Yunfang LIU Ping ZHANG Wei School of Computer Science Nanjing University of Posts and TelecommunicationsNanjing 210023JiangsuChina Jiangsu Key Laboratory of Big Data Security and Intelligent Processing Nanjing University of Posts and TelecommunicationsNanjing 210023JiangsuChina

As one of the underlying technologies of the blockchain,the consensus algorithm plays a vital role in ensuring security and *** a consensus algorithm for the private blockchain,Raft has better performance than the rest of the consensus algorithms,and it does not cause problems such as the concentrated hashing power,resource waste and ***,Raft can only be used in a non-byzantine environment with a small network *** order to enable Raft to be used in a large-scale network with a certain number of byzantine nodes,this paper combines Raft and credit model to propose a Raft blockchain consensus algorithm based on credit model *** the node credit evaluation phase,RBF-based support vector machine is used as the anomaly detection method,and the node credit evaluation model is *** the Trust Nodes List(TNL)mechanism is introduced to make the consensus phase in a creditable network ***,the common node is synchronized to the consensus node to update the blockchain of the entire *** show that CRaft has better throughput and lower latency than the commonly used consortium blockchain consensus algorithm PBFT(Practical Byzantine Fault Tolerance).

关键词： credit model consensus algorithm consortium blockchain P2P network

来源：评论

学校读者我要写书评

暂无评论

Pptcdr: Personalized Preference Transfer Cross-Domain Recommendation Based on Heterogeneous Graph Neural Networks

SSRN

引用

SSRN 2023年

作者： Zhu, Fan Xu, Xiaolong Jiangsu Key Laboratory of Big Data Security and Intelligent Processing Nanjing University of Posts and Telecommunications No. 9 Wenyuan Road Nanjing210023 China School of Computer Science Nanjing University of Posts and Telecommunications No. 9 Wenyuan Road Nanjing210023 China

Cross-domain recommendation methods aim to solve the problems of data sparsity and cold start by leveraging rich information from the source domain to enhance the recommendation accuracy of the target domain. Many methods ignore auxiliary information, which is often structured. Therefore, based on the above issue, we propose a method called PPTCDR (Personalized Preference Transfer Cross-Domain Recommendation) based on heterogeneous graph neural networks. PPTCDR introduces auxiliary information to enrich the information of the source and target domains, alleviates the problem of inaccurate embedding caused by data sparsity, and performs feature embedding of users and items separately in the source and target domains. In addition, for user preference transfer, in order to achieve personalization, a personalized bridging function is provided for each user. PPTCDR first constructs heterogeneous graphs separately in the source and target domains, and learns the latent embeddings of users and items using heterogeneous graph neural networks. Then, a meta-network is used to generate a personalized bridging function for each user. Through the personalized bridging function, the user's embedding in the source domain can be transformed to the target domain, and the transformed user embedding is used as the initial embedding of cold start users in the target domain. In this paper, we set up three cross-domain tasks on the Amazon dataset to verify and compare the performance of the experiment. PPTCDR achieves MAE and RMSE performances of 0.67 and 0.94 respectively, which are respectively improved by 23% and 18% compared to the state-of-the-art works EMCDR and PTUPCDR. © 2023, The Authors. All rights reserved.

关键词： Embeddings

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：