检索结果-内蒙古大学图书馆

2024 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2024

作者： Zhou, Rongzhou Shu, Ziqi Xie, Weixing Yao, Junfeng Hong, Qingqi Xiamen University National Institute for Data Science in Health and Medicine China Xiamen University Center for Digital Media Computing School of Film School of Informatics Xiamen361005 China Key Laboratory of Digital Protection and Intelligent Processing of Intangible Cultural Heritage Fujian and Taiwan Ministry of Culture and Tourism China Xiamen University Institute of Artificial Intelligence Xiamen361005 China

ISBN: (纸本)9798350386226

Self-supervised pre-training followed by fine-tuning is a potent paradigm for few-shot learning, leveraging extensive unlabeled data with remarkable efficacy. Current self-supervised methods often lean towards Vision Transformers (ViTs) rather than CNN-Transformer hybrid architectures, which generally demonstrate superior performance. However, this reliance on ViTs can lead to poor perception of local features by the model. The challenge lies in designing a suitable proxy task for hybrid architectures like CNN-Transformers, which have significant structural differences. Additionally, the current organization of CNN-Transformer hybrid backbones is often sequential, hindering collaboration during pre-training and the acquisition of robust representations. To address these issues, we propose Self-Supervised Collaborative CNN-Transformer (S2CCT) for few-shot medical image segmentation. This framework introduces three innovative designs: (1) a composite proxy task based on image masking and image super-resolution tailored for CNN-Transformer hybrid architectures, enabling the backbone to acquire robust representations during pre-training that can be transferred to downstream tasks;(2) a parallel CNN-Transformer architecture that better attends to multi-scale features in images, making it more suitable for dense prediction tasks like image segmentation;(3) a sparse and dense feature fusion module to enhance collaboration between the two encoders. Experiments demonstrate that S2CCT outperforms previous state-of-the-art methods on two public medical image segmentation benchmarks, i.e., ACDC and KiTs19. The code and pretrained models will be released soon. © 2024 IEEE.

关键词： Image segmentation

来源：评论

学校读者我要写书评

暂无评论

Prompt as Free Lunch: Enhancing Diversity in Source-Free Cross-domain Few-shot Learning through Semantic-Guided Prompting

arXiv

引用

arXiv 2024年

作者： Zhuo, Linhai Wang, Zheng Qian, Tianwen Fu, Yuqian College of Computer and Data Science Fuzhou University Fuzhou China Zhejiang University of Technology College of Computer Science Zhejiang China Key Laboratory of Data Science and Intelligent Computing Hangzhou International Innovation Institute Beihang University Zhejiang China INSAIT Sofia University Bulgaria

The source-free cross-domain few-shot learning (CD-FSL) task aims to transfer pretrained models to target domains utilizing minimal samples, eliminating the need for source domain data. Addressing this issue requires models to have robust generalization abilities and strong feature representation, aligning with the characteristics of large-scale pretrained models. However, large-scale models tend to lose representational ability in cross-domain scenarios due to limited sample diversity. Given the abundant diversity provided by semantic modality, this paper utilize prompt as "free lunch" to enhance the diversity and leverages textual modality to guide the prompt generating. Specifically, we propose the SeGD-VPT framework, which is divided into two phases. The first step aims to increase feature diversity by adding diversity prompts to each support sample, thereby generating varying input and enhancing sample diversity. Furthermore, we use diversity descriptions of classes to guide semantically meaningful learning of diversity prompts, proposing random combinations and selections of texts to increase textual diversity. Additionally, deep prompt tuning is introduced to enhance the model's transfer capability. After training of the first step, support samples with different diversity prompts are input into the CLIP backbone to generate enhanced features. After generation, the second phase trains classifiers using the generated features. Extensive experimental results across several benchmarks verify our method is comparable to SOTA source-utilized models and attain the best performance under the source-free CD-FSL setting. Copyright © 2024, The Authors. All rights reserved.

关键词： Zero-shot learning

来源：评论

学校读者我要写书评

暂无评论

A CLASSIFICATION OF TWO-DISTANCE-TRANSITIVE CAYLEY GRAPHS OVER THE GENERALIZED QUATERNION GROUPS

arXiv

引用

arXiv 2025年

作者： Jin, Wei Li, Ping Shan Tan, Li School of Mathematics and Computational Science Key Laboratory of Intelligent Computing and Information Processing of Ministry of Education Xiangtan University Hunan Xiangtan411105 China School of Statistics and Data Science Jiangxi University of Finance and Economics Jiangxi Nanchang330013 China School of Mathematics and Statistics Key Laboratory of Intelligent Computing and Information Processing of Ministry of Education Xiangtan University Hunan Xiangtan411105 China

A non-complete graph is 2-distance-transitive if, for i = 1, 2 and for any two vertex pairs (u1, v1) and (u2, v2) with the same distance i in the graph, there exists an element of the graph automorphism group that maps (u1, v1) to (u2, v2). This is a generalization concept of the classical well-known distance-transitive graphs. In this paper, we completely determine the family of 2-distance-transitive Cayley graphs over the generalized quaternion groups. Copyright © 2025, The Authors. All rights reserved.

关键词：

来源：评论

学校读者我要写书评

暂无评论

ES-GP: An Ensemble Surrogate-Assisted Genetic Programming Approach to Image Classification

引用

IEEE Transactions on Evolutionary Computation 2025年

作者： Fan, Qinglan Zhang, Yunfeng Yao, Xunxiang Bi, Ying Xue, Bing Zhang, Mengjie Shandong University of Finance and Economics School of Computing and Artificial Intelligence Shandong Key Laboratory of Lightweight Intelligent Computing and Visualization for Digital Economy Jinan250014 China Zhengzhou University School of Electrical and Information Engineering Zhengzhou450001 China State Key Laboratory of Intelligent Agricultural Power Equipment Luoyang471000 China Victoria University of Wellington Center for Data Science and Artificial Intelligence School of Engineering and Computer Science Wellington6140 New Zealand

Genetic Programming (GP) is a promising evolutionary machine learning technique for image classification, known for its ability to evolve flexible, effective, and interpretable models. However, the high computational cost of fitness evaluations in evolutionary learning restricts its practical applications. While Surrogate models offer efficient approximations for costly fitness evaluations, their application in GP-based image classification remains in its early stages, facing challenges such as handing flexible tree-based representations with variable lengths, designing an effective surrogate, and the limited performance of a single surrogate across various image classification tasks. To address these issues, this paper proposes an ensemble surrogate-assisted GP approach to image classification. The new approach constructs one global surrogate model to explore broad areas and three local surrogate models within specific subspaces to exploit local regions, enabling more accurate predictions of GP individuals' fitness. Moreover, a dynamic weighting strategy is developed to assign different weights to the base surrogate models in the ensemble, improving prediction accuracy. Additionally, the proposed approach refines the surrogate training set1 construction method, previously limited to single-tree GP, enabling it to accelerate both single-tree and multi-tree GP 2 for image classification. Experimental results on five datasets of varying difficulty demonstrate that the new ensemble surrogate method significantly reduces the number of expensive fitness evaluations of both single-tree and multi-tree GP-based image classification methods while achieving competitive performance. The comparisons with other state-of-the-art methods also confirm its effectiveness. © 1997-2012 IEEE.

关键词： Genetic algorithms

来源：评论

学校读者我要写书评

暂无评论

Drug-Protein Interaction Prediction by Fusion of Attention and Graph Neural Network

Drug-Protein Interaction Prediction by Fusion of Attention a...

引用

Chinese Control Conference (CCC)

作者： Tianrui Chen Shouheng Tuo Zengyu Feng School of Computer Science and Technology Xi'an University of Posts and Telecommunications Xi'an Shaanxi China Shaanxi Key Laboratory of Network Data Analysis and Intelligent Processing Xi'an Shaanxi China Xi'an Key Laboratory of Big Data and Intelligent Computing Xi'an Shaanxi China

The identification of drug-protein interactions (DTIs) is a critical step in drug development and repositioning. However, detecting these interactions using scientific methods presents a formidable challenge. Existing models often struggle to extract relevant information from drug-protein sequences, and they fail to consider pre-existing interactions between pairs. Here, we introduce a deep learning model, DPAG, based on attention mechanisms and graph neural networks, which overcomes these limitations. DPAG leverages information from both the drug and protein sequences, as well as the association between drug-protein pairs, to predict DTIs. We conducted multiple experiments to evaluate the performance of the model in benchmark datasets, and the results showed that DPAG achieved excellent performance in terms of AUC, AUPR, precision, and recall. Our findings suggest that DPAG holds significant potential as a promising tool for predicting DTIs in drug development and repositioning. Code is available at https://***/veresse/DPAG.

关键词：

来源：评论

学校读者我要写书评

暂无评论

A New Model Based on Differential Evolutionary Algorithm and Markov Clustering for Identifying Protein Complexes

A New Model Based on Differential Evolutionary Algorithm and...

引用

Chinese Control Conference (CCC)

作者： Zengyu Feng Shouheng Tuo Tianrui Chen School of Computer Science and Technology Xi'an University of Posts and Telecommunications Xi'an Shaanxi China Shaanxi Key Laboratory of Network Data Analysis and Intelligent Processing Xi'an Shaanxi China Xi'an Key Laboratory of Big Data and Intelligent Computing Xi'an Shaanxi China

As the material basis for all life activities, proteins play a crucial role in performing life activities. Most real-life proteins perform various functions in the form of protein complexes, so it is essential for understanding of life activities to accurately identify protein complexes. Most of the existing approaches learn protein interactions directly from protein topology, ignoring the biological characteristics of the actual proteins. Nevertheless, actual protein complexes are usually composed of protein cores and protein attachments. In this study, a new MP-DE algorithm is designed from the core-attachment structure to generate protein complex cores using Markov clustering, while searching for attached proteins in the second-order neighborhood of core protein complexes based on differential evolution(DE) algorithm. The experimental results show that the proposed method has high detection accuracy and efficiency on the current mainstream protein-protein interaction(PPI) database.

关键词：

来源：评论

学校读者我要写书评

暂无评论

DEGSTalk: Decomposed Per-Embedding Gaussian Fields for Hair-Preserving Talking Face Synthesis

DEGSTalk: Decomposed Per-Embedding Gaussian Fields for Hair-...

引用

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

作者： Kaijun Deng Dezhi Zheng Jindong Xie Jinbao Wang Weicheng Xie Linlin Shen Siyang Song Computer Vision Institute School of Computer Science and Software Engineering Shenzhen University National Engineering Laboratory for Big Data System Computing Technology Shenzhen University Guangdong Provincial Key Laboratory of Intelligent Information Processing Department of Computer Science University of Exeter

ISBN: (数字)9798350368741

ISBN: (纸本)9798350368758

Accurately synthesizing talking face videos and capturing fine facial features for individuals with long hair presents a significant challenge. To tackle these challenges in existing methods, we propose a decomposed per-embedding Gaussian fields (DEGSTalk), a 3D Gaussian Splatting (3DGS)-based talking face synthesis method for generating realistic talking faces with long hairs. Our DEGSTalk employs Deformable Pre-Embedding Gaussian Fields, which dynamically adjust pre-embedding Gaussian primitives using implicit expression coefficients. This enables precise capture of dynamic facial regions and subtle expressions. Additionally, we propose a Dynamic Hair-Preserving Portrait Rendering technique to enhance the realism of long hair motions in the synthesized videos. Results show that DEGSTalk achieves improved realism and synthesis quality compared to existing approaches, particularly in handling complex facial dynamics and hair preservation. Our code is available at https://***/CVI-SZU/DEGSTalk.

关键词： Hair Training Three-dimensional displays Dynamics Signal processing Rendering (computer graphics) Noise measurement Speech processing Faces Videos

来源：评论

学校读者我要写书评

暂无评论

Improving Controllability of Chaotic Landscape Generators by Property Evolution

Improving Controllability of Chaotic Landscape Generators by...

引用

Congress on Evolutionary Computation

作者： Bo Zhang Fengyang Sun Lin Wang Bo Yang Shandong Provincial Key Laboratory of Green and Intelligent Building Materials University of Jinan Jinan China Centre for Data Science and Artificial Intelligence & School of Engineering and Computer Science Victoria University of Wellington Wellington New Zealand Shandong Provincial Key Laboratory of Ubiquitous Intelligent Computing University of Jinan Jinan China Quan Cheng Laboratory Jinan China

ISBN: (数字)9798331534318

ISBN: (纸本)9798331534325

As optimization algorithms progress to address more complex and high-dimensional challenges, the need for benchmark problems that are both diverse and controllable has become crucial for effective performance evaluation. However, traditional benchmark problem generators often fall short in capturing the required diversity and controllability, limiting their effectiveness in assessing algorithm performance. This paper introduces a novel Controllable Chaotic Landscape Generator (CCLG), designed to enhance the controllability of generated landscapes through the integration of optimization techniques, while maintaining high diversity. This study leverages common problem attributes from the BBOB benchmark suite as targets, enabling effective control over both local and global characteristics of the generated problems, such as the positions of local optima, condition numbers, ruggedness, and global structure. Experimental results demonstrate that CCLG not only achieves effective control over landscape features but also preserves high diversity to meet various optimization requirements.

关键词： Performance evaluation Monte Carlo methods Limiting Scalability Evolutionary computation Benchmark testing Controllability Generators Iterative methods Optimization

来源：评论

学校读者我要写书评

暂无评论

UNeLF: Unconstrained Neural Light Field for Self-Supervised Angular Super-Resolution

引用

IEEE Transactions on Circuits and Systems for Video Technology 2025年

作者： Zhao, Mingyuan Sheng, Hao Chen, Rongshan Cong, Ruixuan Cui, Zhenglong Yang, Da Beihang University State Key Laboratory of Virtual Reality Technology and Systems School of Computer Science and Engineering Beijing100191 China Beihang University Data Science and Intelligent Computing Laboratory Hangzhou International Innovation Institute Hangzhou311115 China Macao Polytechnic University Faculty of Applied Sciences 999078 China

Compared to supervised learning methods, self-supervised learning methods address the domain gap problem between light field (LF) datasets collected under varying acquisition conditions, which typically leads to decreased performance when differences exist in the distribution between the training and test sets. However, current self-supervised light field angular super-resolution (LFASR) techniques primarily focus on exploiting discrete spatial-angular features while neglecting continuous LF information. In contrast to previous work, we propose a self-supervised unconstrained neural light field (UNeLF) to continuously represent LF for LFASR. Specifically, any LF can be described as the camera pose for each sub-aperture image (SAI) and the two-plane that captures these SAIs. To describe the former, we introduce a SAIs-dependent pose optimization method to solve the issue that arises from the narrow baseline of most LF data, which hinders robust camera pose estimation. This mechanism reduces the number of trainable camera parameters from a quadratic to a constant scale, thereby alleviating the complexity of joint optimization. For the latter, we propose a novel adaptive two-plane parameterization strategy to determine the two-plane that captures these SAIs, facilitating refocusing. Finally, we jointly optimize the camera parameters, near-far planes and neural light field, efficiently mapping each adaptive two-plane parameterized ray to its correspondence color in a continuous manner. Comprehensive experiments demonstrate that UNeLF achieves faster training and inference with fewer computational resources while exhibiting superior performance on both synthetic and real-world datasets. © 1991-2012 IEEE.

关键词： Self-supervised learning

来源：评论

学校读者我要写书评

暂无评论

Hierarchical Context Pruning: Optimizing Real-World Code Completion with Repository-Level Pretrained Code LLMs 39

Hierarchical Context Pruning: Optimizing Real-World Code Com...

引用

39th Annual AAAI Conference on Artificial Intelligence, AAAI 2025

作者： Zhang, Lei Li, Yunshui Li, Jiaming Xia, Xiaobo Yang, Jiaxi Luo, Run Wang, Minzheng Chen, Longze Liu, Junhao Qu, Qiang Yang, Min Shenzhen Key Laboratory for High Performance Data Mining Shenzhen Institutes of Advanced Technology Chinese Academy of Sciences China University of Chinese Academy of Sciences China Key Laboratory of Intelligent Education Technology Application of Zhejiang Province Zhejiang Normal University China School of Computing National University of Singapore Singapore University of Science and Technology of China China University of California Irvine United States MAIS Institute of Automation Chinese Academy of Sciences China

ISBN: (纸本)157735897X

Some of the latest released Code Large Language Models (Code LLMs) have been trained on repository-level code data, enabling them to perceive repository structures and utilize cross-file code information. This capability allows us to directly concatenate the content of repository code files in prompts to achieve repository-level code completion. However, in real development scenarios, directly concatenating all code repository files in a prompt can easily exceed the context window of Code LLMs, leading to a significant decline in completion performance. Additionally, overly long prompts can increase completion latency, negatively impacting the user experience. In this study, we conducted extensive experiments, including completion error analysis, topology dependency analysis, and cross-file content analysis, to investigate the factors affecting repository-level code completion. Based on the conclusions drawn from these preliminary experiments, we proposed a strategy called Hierarchical Context Pruning (HCP) to construct high-quality completion prompts. We applied the HCP to six Code LLMs and evaluated them on the CrossCodeEval dataset. The experimental results showed that, compared to previous methods, the prompts constructed using our HCP strategy achieved higher completion accuracy on five out of six Code LLMs. Additionally, the HCP managed to keep the prompt length around 8k tokens (whereas the full repository code is approximately 50k tokens), significantly improving completion throughput. Our code and data will be publicly available. © 2025, Association for the Advancement of Artificial Intelligence (***). All rights reserved.

关键词： High level languages

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：