检索结果-内蒙古大学图书馆

Towards Synchronous Memorizability and Generalizability with Site-Modulated Diffusion Replay for Cross-Site Continual Segmentation

引用

IEEE Transactions on Medical Imaging 2025年 PP卷 PP页

作者： Xu, Dunyuan Wang, Xi Li, Jinpeng Zhang, Jingyang Heng, Pheng-Ann Department of Computer Science and Engineering Chinese University of Hong Kong Hong Kong Institute of Medical Intelligence and XR Chinese University of Hong Kong Hong Kong Hong Kong University of Science and Technology Department of Computer Science and Engineering China Southeast University School of Computer Science and Engineering Key Laboratory of New Generation Artiﬁcial Intelligence Technology and Interdisciplinary Applications China

The ability to learn sequentially from different data sites is crucial for a deep network in solving practical medical image diagnosis problems due to privacy restrictions and storage limitations. However, adapting to the incoming site leads to catastrophic forgetting on past sites and decreases generalizability on unseen sites. Existing Continual Learning (CL) and Domain Generalization (DG) methods have been proposed to solve these two challenges respectively, but none of them can address both simultaneously. Recognizing this limitation, this paper proposes a novel training paradigm, learning towards Synchronous Memorizability and Generalizability (SMG-Learning). To achieve this, we create the orientational gradient alignment to ensure memorizability on previous sites, and arbitrary gradient alignment to enhance generalizability on unseen sites. This approach is called Parallel Gradient Alignment (PGA). Furthermore, we approximate the PGA as dual meta-objectives using the first-order Taylor expansion to reduce the computational cost of aligning gradients. Considering that performing gradient alignments, especially for previous sites, is not feasible due to privacy constraints, we design a Site-Modulated Diffusion (SMD) model to generate images with site-specific learnable prompts, replaying images have similar data distributions as previous sites. We evaluate our method on two medical image segmentation tasks, where data from different sites arrive sequentially. Experimental results show that our method efficiently enhances both memorizability and generalizability better than other state-of-the-art methods, delivering satisfactory performance across all sites. © 1982-2012 IEEE.

关键词： Image segmentation

来源：评论

学校读者我要写书评

暂无评论

Beyond Overfitting: Doubly Adaptive Dropout for Generalizable AU Detection

arXiv

引用

arXiv 2025年

作者： Li, Yong Ren, Yi Niu, Xuesong Ding, Yi Wei, Xiu-Shen Guan, Cuntai School of Computer Science and Engineering The Key Laboratory of New Generation Artificial Intelligence Technology and Its Interdisciplinary Applications Southeast University Nanjing210096 China School of Computer Science and Engineering Nanjing University of Science and Technology Nanjing210094 China Beijing Institute for General Artificial Intelligence Beijing China School of Computer Science and Engineering Key Laboratory of New Generation Artificial Intelligence Technology and Its Interdisciplinary Applications Southeast University Nanjing210096 China School of Computer Science and Engineering Nanyang Technological University 50 Nanyang Avenue 639798 Singapore

Facial Action Units (AUs) are essential for conveying psychological states and emotional expressions. While automatic AU detection systems leveraging deep learning have progressed, they often overfit to specific datasets and individual features, limiting their cross-domain applicability. To overcome these limitations, we propose a doubly adaptive dropout approach for cross-domain AU detection, which enhances the robustness of convolutional feature maps and spatial tokens against domain shifts. This approach includes a Channel Drop Unit (CD-Unit) and a Token Drop Unit (TD-Unit), which work together to reduce domain-specific noise at both the channel and token levels. The CD-Unit preserves domain-agnostic local patterns in feature maps, while the TD-Unit helps the model identify AU relationships generalizable across domains. An auxiliary domain classifier, integrated at each layer, guides the selective omission of domain-sensitive features. To prevent excessive feature dropout, a progressive training strategy is used, allowing for selective exclusion of sensitive features at any model layer. Our method consistently outperforms existing techniques in cross-domain AU detection, as demonstrated by extensive experimental evaluations. Visualizations of attention maps also highlight clear and meaningful patterns related to both individual and combined AUs, further validating the approach’s effectiveness. © 2025, CC BY-NC-SA.

关键词： Deep learning

来源：评论

学校读者我要写书评

暂无评论

Beyond Overfitting: Doubly Adaptive Dropout for Generalizable AU Detection

引用

IEEE Transactions on Affective Computing 2025年

作者： Li, Yong Ren, Yi Niu, Xuesong Ding, Yi Wei, Xiu-Shen Guan, Cuntai School of Computer Science and Engineering Nanjing University of Science and Technology Nanjing210094 China Beijing Institute for General Artificial Intelligence Beijing China School of Computer Science and Engineering Key Laboratory of New Generation Artificial Intelligence Technology and Its Interdisciplinary Applications Southeast University China School of Computer Science and Engineering Nanyang Technological University 50 Nanyang Avenue Singapore639798 Singapore

关键词： Deep learning

来源：评论

学校读者我要写书评

暂无评论

RESEARCH ON PARALLEL MACHINE ARCHITECTURE FOR 5TH-generation computer-SYSTEMS

引用

computer 1985年第6期18卷 76-92页

作者： MURAKAMI, K KAKUTA, T ONAI, R ITO, N Institute for New Generation Computer Technology

The authors describe the multiprocessing and parallel processing techniques being built into the core hardware of the fifth-generation computer system -- the parallel inference and knowledge base machines. The two machines are currently being studied and developed as separate research subsets. Efforts to integrate them into a total hardware system will start during the intermediate stage of the Japanese effort to produce fifth-generation systems.

关键词： Parallel machines computer architecture Concurrent computing Parallel processing Research and development Inference algorithms Inference mechanisms

来源：评论

学校读者我要写书评

暂无评论

A new EXTERNAL REFERENCE MANAGEMENT AND DISTRIBUTED UNIFICATION FOR KL1

引用

new generation COMPUTING 1990年第2-3期7卷 159-177页

作者： ICHIYOSHI, N ROKUSAWA, K NAKAJIMA, K INAMURA, Y Institute for New Generation Computer Technology Tokyo Japan

This paper describes a new external reference management scheme for KL1, a committed choice logic programming language based on GHC. The significance of the new scheme is that it realizes incremental inter-processor garbage collection. Previous distributed implementations of committed choice languages had not seriously addressed inter-processor garbage collection. Incremental inter-precessor garbage collection is realized by the Weighted Export Counting (WEC). It is a first attempt to use the weighted reference counting technique in logic programming language implementation, and is also new in that it has introduced export and import tables for making independent local garbage collection possible and reducing the number of inter-processor read requests. The problems with exhaustion of reference counts and indirect exportation are discussed. Since the binding order rule adopted in our previous implementation for avoiding creation of reference loops is insufficient in the presence of indirect exportation, a new binding order rule is introduced. We prove that avoidance of reference loops is guaranteed and also prove that the unification procedure always terminates for non-circular structures.

关键词： Concurrent Logic Language Distributed Unification Implementation Inter-processor Garbage Collection Loosely-coupled Multiprocessor Weighted Export Counting

来源：评论

学校读者我要写书评

暂无评论

PARTIAL EVALUATION OF QUERIES IN DEDUCTIVE DATABASES

引用

new generation COMPUTING 1988年第2-3期6卷 249-258页

作者： SAKAMA, C ITOH, H Institute for New Generation Computer Technology Tohyo Japan

This paper presents some applications of partial evaluation method to a query optimization in deductive database. A Horn clause transformation is used for the partial evaluation of a query in an intensional database, and its application to multiple query processing is discussed. Three strategies are presented for the compatible case, ordered case and crossed case. In each case, partial evaluation is used to preprocess the intensional database in order to obtain subqueries which direct access to an extensional database.

关键词： Deductive Database Horn Clause Transformation Multiple Query Processing Partial Evaluation Query Optimization

来源：评论

学校读者我要写书评

暂无评论

Multi-Scale Cascaded with Cross-Attention Network-Based Deformation Vector Field Estimation for Motion-Compensated 4D-CBCT Reconstruction

IEEE Transactions on Computational Imaging

引用

IEEE Transactions on Computational Imaging 2025年

作者： Yuan, Peng Lyu, Fei Gao, Zhiqiang Yang, Chunfeng Hu, Dianlin Zhu, Jian Wu, Zhan Lyu, Tianling Zhao, Wei Dong, Jianmin Chen, Yang Key Laboratory of New Generation Artificial Intelligence Technology and Its Interdisciplinary Applications Ministry of Education Southeast University Nanjing210096 China Laboratory of Image Science and Technology Southeast University Nanjing210096 China Department of Computer Science Hong Kong Baptist University Hong Kong Hong Kong Academy for Advanced Interdisciplinary Science and Technology Zhejiang University of Technology Hangzhou China School of Physics Beihang University Beijing China Beihang Hangzhou Innovation Institute Zhejiang Hangzhou China School of Shandong Cancer Hospital and Institute Shandong First Medical University Shandong Academy of Medical Sciences Jinan Shandong China School of Information Engineering Xizang Minzu University Xianyang712082 China Jiangsu Provincial Joint International Research Laboratory of Medical Information Processing The Laboratory of Image Science and Technology The School of Computer Science and Engineering Key Laboratory of New Generation Artificial Intelligence Technology and Its Interdisciplinary Applications Southeast University Ministry of Education Nanjing210096 China

Four-Dimensional Cone Beam Computed Tomography (4D-CBCT) imaging technology offers enhanced image quality and spatial resolution for intraoperative guidance, facilitating real-time tracking of tumor position changes during radiotherapy. However, this is still a task of great challenges due to insufficient projections at each respiratory phase after phase-sorting, and the image phases reconstructed directly from phase-sorted data are discrete and discontinuous. To generate high-quality 4D-CBCT deformation vector fields (DVFs), this paper leverages the preoperative static prior image to guide intraoperative dynamic sparse-view reconstruction images for reducing anatomical structure differences, ultimately achieving continuous and dynamic 4D-CBCT imaging. In this paper, we propose a Multi-scale Cascaded residual deformable vector field estimation framework based on Cross-attention in Motioncompensated 4D-CBCT reconstruction (MCCM), which combines Multi-Scale Cascaded residual registration network (MSCNet), Cross-Attention Enhanced feature Fusion (CAEF) module and Structure-Enhanced Motion-Compensated (SEMC) module: 1) the MCCM employs a multi-scale cascaded residual network strategy, merging multi-receptive fields and multi-resolution feature maps for large-scale internal changes. 2) the CAEF is embedded into MSC-Net to facilitate effective communication and learning between features and promote the flow of information. 3) the SEMC is developed to reduce artifacts after intraoperative CBCT sparse-view reconstruction, restore global lung motion changes and local details, and enhance structural information through image fusion. The proposed method has been evaluated using simulated and clinical datasets and has shown promising results by comparative experiment. Our approach exhibits significant improvements across various evaluation metrics. © 2024 IEEE.

关键词： Image fusion

来源：评论

学校读者我要写书评

暂无评论

PREFERENCE-BASED DECISION-MAKING FOR COOPERATIVE KNOWLEDGE-BASED SYSTEMS

引用

ACM TRANSACTIONS ON INFORMATION SYSTEMS 1994年第4期12卷 407-435页

作者： WONG, STC Institute for New Generation Computer Technology (ICOT) Tokyo Japan

Recent advances in cooperative knowledge-based systems (CKBS) offer significant promise for intelligent interaction between multiple AI systems for solving larger, more complex problems. In this paper, we propose a logical, qualitative problem-solving scheme for CKBS that uses social choice theory as a formal basis for making joint decisions and promoting conflict resolution. This scheme consists of three steps: (1) the selection of decision criteria and competing alternatives, (2) the formation of perference profiles and collective choices, and (3) the negotiation among agents as conflicts arise in group decision making. In this paper, we focus on the computational mechanisms developed to support steps (2) and (3) of the scheme. In addition, the practicality of the scheme is illustrated with examples taken from a working prototype dealing with collaborative structural design of buildings.

关键词： COOPERATIVE PROBLEM SOLVING COOPERATIVE KNOWLEDGE-BASED SYSTEMS DECISION MAKING SOCIAL CHOICE THEORY

来源：评论

学校读者我要写书评

暂无评论

THE NUCLEUS OF FUTURE COMPUTING - PREFACE

引用

new generation COMPUTING 1989年第1期7卷 1-2页

作者： FUCHI, K Institute for New Generation Computer Technology Tokyo Japan

来源：评论

学校读者我要写书评

暂无评论

A'UM - A STREAM-BASED CONCURRENT OBJECT-ORIENTED LANGUAGE

引用

new generation COMPUTING 1990年第2-3期7卷 127-157页

作者： YOSHIDA, K CHIKAYAMA, T ICOT Research Center Institute for New Generation Computer Technology Tokyo Japan

This paper presents a computation model and its programming language,A’UM,* as a result of our pursuit of high parallelism and high expressivity for the development of a large scale software. By basing it on streams and integrating it with objects and relations,A’UM realizes an elegant model, natural representation and efficient execution, all at once, that have never been done by any other approaches.

关键词： Concurrent Programming Language Object-oriented Stream

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：