检索结果-内蒙古大学图书馆

A decoder-free feature aggregation network for medical image segmentation

Multimedia Tools and Applications 2025年第10期84卷 7047-7064页

作者： Ni, Jiajia Mu, Wei Pan, An Chen, Zhengming School of Artificial Intelligence Anhui Polytechnic University Wuhu241000 China School of Information Science and Engineering HoHai University Changzhou213000 China

Encoder-decoder structured networks have recently become dominant in medical image segmentation, primarily due to their straightforward architecture. However, their extensive use of up-sampling operations, aimed at expanding network parameters, often leads to feature information loss. To address this issue, we propose a novel, decoder-free architecture for medical image segmentation, termed Feature Aggregation Network (FAN-Net). This approach eliminates both the pooling operation and the decoder phase, directly addressing the loss of feature information. During the encoding phase, we replace the traditional pooling operation with the patch merge attention (PMA) module, which systematically reduces feature map dimensionality. Despite omitting the decoding structure, the necessity to restore feature map resolution remains. To this end, we introduce the multi-path feature aggregation (MFA) module, which reinstates feature map dimensionality. Additionally, we propose an adaptive attention feature (AAF) extraction module, engineered to enhance semantic representation distinctiveness. We conduct extensive experiments on popular semantic segmentation benchmarks including IXI dataset, DRIVE, and CHASEDB. The experimental results demonstrate the effectiveness of the proposed FAN-Net, which is capable of achieving better segmentation performance than other state-of-the-art approaches. In addition, this paper also shows that medical image segmentation can be performed without necessitating the deployment of the decoder stage. © The Author(s), under exclusive licence to Springer science+Business Media, LLC, part of Springer Nature 2024.

关键词： Semantic Segmentation

来源：评论

学校读者我要写书评

暂无评论

NeuroProbe: A Performance Profiling Feed Forward Neural Network Simulator for Hardware Interaction Analysis

引用

SN computer science 2025年第5期6卷 1-22页

作者： Ayyappan, Binu Kumar, G. Santhosh Department of Computer Science Cochin University of Science and Technology Kochi India Department of Artificial Intelligence and Data Science Rajagiri School of Engineering & Technology Kochi India

NeuroProbe is a simple neural network simulator designed by authors specifically for educational purposes focusing on simulating inference phase on a computationally capable embedded hardware, aiming to provide a deeper understanding of hardware interactions and performance improvement. This simulator incorporates performance profiling capabilities, allowing students and educators to analyze and optimize the performance of a simulated trained neural network. By simulating the intricate hardware interactions, NeuroProbe enables users to gain insights into how various components impact the overall performance of neural networks. Using this simulator, learners can experiment with different configurations and architectures, identify potential bottlenecks, and explore optimization strategies to enhance neural network performance before deploying the model on an Edge Computing environment. It also enriches computer science education by enabling learners to gain deeper insights into hardware interactions and performance improvement. By identifying performance bottlenecks, learners can refine their understanding of neural networks and develop skills in optimizing their models for enhanced performance. In conclusion, NeuroProbe empowers users to bridge the gap between theoretical knowledge and practical implementation of neural network on an embedded device, fostering a more comprehensive understanding of neural networks and their hardware requirements. Currently, it is focused solely on single-threaded CPU-based computation enabling SSE, AVX. At present, NeuroProbe does not support SIMD extensions such as AVX-FMA, AVX-512, multi-threaded computation, and accelerators such as NPU, TPU, and GPU. © The Author(s), under exclusive licence to Springer Nature Singapore Pte Ltd. 2025.

关键词： Hardware–software interactions Neural network simulator NeuroProbe Performance bottlenecks Performance profiling Simulations

来源：评论

学校读者我要写书评

暂无评论

Efficient RGBT Tracking via Multi-Path Mamba Fusion Network

引用

IEEE Signal Processing Letters 2025年 32卷 1790-1794页

作者： Hong, Fanghua Wang, Wanyu Lu, Andong Liu, Lei Wang, Qunjing Anhui University School of Electronic Information Engineering Hefei230601 China Anhui University School of Artificial Intelligence Hefei230601 China Anhui University Anhui Provincial Key Laboratory of Multimodal Cognitive Computation School of Computer Science and Technology Hefei230601 China Anhui University of Science and Technology School of Artificial Intelligence Hefei230601 China

RGBT tracking aims to fully exploit the complementary advantages of visible and infrared modalities to achieve robust tracking, thus the design of multimodal fusion network is crucial. However, existing methods typically adopt CNNs or Transformer networks to construct the fusion network, which poses a challenge in achieving a balance between performance and efficiency. To overcome this issue, we introduce an innovative visual state space (VSS) model, represented by Mamba, for RGBT tracking. In particular, we design a novel multi-path Mamba fusion network that achieves robust multimodal fusion capability while maintaining a linear overhead. First, we design a multi-path Mamba layer to sufficiently fuse two modalities in both global and local perspectives. Second, to alleviate the issue of inadequate VSS modeling in the channel dimension, we introduce a simple yet effective channel swapping layer. Extensive experiments conducted on four public RGBT tracking datasets demonstrate that our method surpasses existing state-of-the-art trackers. Notably, our fusion method achieves higher tracking performance compared to the well-known Transformer-based fusion approach (TBSI), while also achieving 92.8% and 80.5% reductions in parameter count and computational cost, respectively. © 1994-2012 IEEE.

关键词： Alignment

来源：评论

学校读者我要写书评

暂无评论

Learning to Refuse: Towards Mitigating Privacy Risks in LLMs 31

Learning to Refuse: Towards Mitigating Privacy Risks in LLMs

引用

31st International Conference on Computational Linguistics, COLING 2025

作者： Liu, Zhenhua Zhu, Tong Tan, Chuanyuan Chen, Wenliang Institute of Artificial Intelligence School of Computer Science and Technology Soochow University China

ISBN: (纸本)9798891761964

Large language models (LLMs) exhibit remarkable capabilities in understanding and generating natural language. However, these models can inadvertently memorize private information, posing significant privacy risks. This study addresses the challenge of enabling LLMs to protect specific individuals' private data without the need for complete retraining. We propose RETURN, a Real-world pErsonal daTa UnleaRNing dataset, comprising 2,492 individuals from Wikipedia with associated QA pairs, to evaluate machine unlearning (MU) methods for protecting personal data in a realistic scenario. Additionally, we introduce the Name-Aware Unlearning Framework (NAUF) for Privacy Protection, which enables the model to learn which individuals' information should be protected without affecting its ability to answer questions related to other unrelated individuals. Our extensive experiments demonstrate that NAUF achieves a state-of-the-art average unlearning score, surpassing the best baseline method by 5.65 points, effectively protecting target individuals' personal data while maintaining the model's general capabilities. © 2025 Association for Computational Linguistics.

关键词： Differential privacy

来源：评论

学校读者我要写书评

暂无评论

NESTOOLS: A Dataset for Evaluating Nested Tool Learning Abilities of Large Language Models 31

NESTOOLS: A Dataset for Evaluating Nested Tool Learning Abil...

引用

31st International Conference on Computational Linguistics, COLING 2025

作者： Han, Han Zhu, Tong Zhang, Xiang Wu, Mengsong Xiong, Hao Chen, Wenliang Institute of Artificial Intelligence School of Computer Science and Technology Soochow University China

ISBN: (纸本)9798891761964

Large language models (LLMs) combined with tool learning have gained impressive results in real-world applications. During tool learning, LLMs may call multiple tools in nested orders, where the latter tool call may take the former response as its input parameters. However, current research on the nested tool learning capabilities is still under-explored, since the existing benchmarks lack relevant data instances. To address this problem, we introduce NESTOOLS to bridge the current gap in comprehensive nested tool learning evaluations. NESTOOLS comprises a novel automatic data generation method to construct large-scale nested tool calls with different nesting structures. With manual review and refinement, the dataset is in high quality and closely aligned with real-world scenarios. Therefore, NESTOOLS can serve as a new benchmark to evaluate the nested tool learning abilities of LLMs. We conduct extensive experiments on 22 LLMs, and provide in-depth analyses with NESTOOLS, which shows that current LLMs still suffer from the complex nested tool learning task. © 2025 Association for Computational Linguistics.

关键词： Contrastive Learning

来源：评论

学校读者我要写书评

暂无评论

Node ranking based on graph curvature and PageRank

引用

Chinese Physics B 2025年第2期34卷 496-507页

作者： Hongbo Qu Yu-Rong Song Ruqi Li Min Li Guo-Ping Jiang School of Computer Science Nanjing University of Posts and TelecommunicationsNanjing 210023China College of Automation&College of Artificial Intelligence Nanjing University of Posts and TelecommunicationsNanjing 210023China

Identifying key nodes in complex networks is crucial for understanding and controlling their dynamics. Traditional centrality measures often fall short in capturing the multifaceted roles of nodes within these networks. The Page Rank algorithm, widely recognized for ranking web pages, offers a more nuanced approach by considering the importance of connected nodes. However, existing methods generally overlook the geometric properties of networks, which can provide additional insights into their structure and functionality. In this paper, we propose a novel method named Curv-Page Rank(C-PR), which integrates network curvature and Page Rank to identify influential nodes in complex networks. By leveraging the geometric insights provided by curvature alongside structural properties, C-PR offers a more comprehensive measure of a node's influence. Our approach is particularly effective in networks with community structures, where it excels at pinpointing bridge nodes critical for maintaining connectivity and facilitating information flow. We validate the effectiveness of C-PR through extensive experiments. The results demonstrate that C-PR outperforms traditional centrality-based and Page Rank methods in identifying critical nodes. Our findings offer fresh insights into the structural importance of nodes across diverse network configurations, highlighting the potential of incorporating geometric properties into network analysis.

关键词： important nodes graph curvature complex networks network geometry

来源：评论

学校读者我要写书评

暂无评论

Self-Supervised Learning and Image-Prompt Fusion for AIGC Image Quality Assessment

Self-Supervised Learning and Image-Prompt Fusion for AIGC Im...

引用

2025 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2025

作者： Zhao, Yan Sang, Qingbing Deng, Zhaohong Wu, Xiaojun The School of Artificial Intelligence and Computer Science Jiangnan University Wuxi214122 China

ISBN: (纸本)9798350368741

With the rapid advancement of artificial intelligence, the field of artificial intelligence Generated Content (AIGC) has seen significant growth. As AI-generated images (AIGIs) become increasingly prevalent, the AIGC image quality assessment(AIGCIQA) has gained critical importance. However, traditional image quality assessment methods struggle to account for the complex relationship between generated images and their corresponding text prompts, leading to suboptimal performance in AIGCIQA tasks. Additionally, the scarcity of subjective annotation data within AIGCIQA datasets limits the effectiveness of deep learning models. To address these challenges, we propose a novel self-supervised task that utilizes intermediate image sequences generated during Text-to-Image (T2I) model generation as the pre-training data. We use the number of model iterations as pseudo-labels based on the positive correlation between image quality and the number of model iterations. Due to the relative coarseness of this pseudo-label as a supervised signal, we also introduce a linear interpolation method for optimization. Additionally, we designed a framework that effectively fuses image and text features. The framework considers the dynamic fading properties of intermediate image sequences similar to video clips. It utilizes a specialized text prompt template and extracts image features through a cross-attention mechanism, which significantly improves model performance. Experimental results show that the proposed method achieves state-of-the-art performance on three mainstream AIGCIQA datasets. © 2025 IEEE.

关键词： AI-generated images image quality assessment self-supervised learning

来源：评论

学校读者我要写书评

暂无评论

Maximum Power Point Tracking Control of Offshore Wind-Photovoltaic Hybrid Power Generation System with Crane-Assisted

引用

computer Modeling in engineering & sciences 2025年第4期143卷 289-334页

作者： Xiangyang Cao Yaojie Zheng Hanbin Xiao Min Xiao School of Transportation and Logistics Engineering Wuhan University of TechnologyWuhan430063China Sanya Science and Education Innovation Park Wuhan University of TechnologySanya572024China School of Computer Science and Artificial Intelligence Wuhan University of TechnologyWuhan430063China

This study investigates the Maximum Power Point Tracking(MPPT)control method of offshore windphotovoltaic hybrid power generation system with offshore crane-assisted.A new algorithm of Global Fast Integral Sliding Mode Control(GFISMC)is proposed based on the tip speed ratio method and sliding mode *** algorithm uses fast integral sliding mode surface and fuzzy fast switching control items to ensure that the offshore wind power generation system can track the maximum power point quickly and with low *** offshore wind power generation system model is presented to verify the algorithm *** offshore off-grid wind-solar hybrid power generation systemis built in MATLAB/*** with other MPPT algorithms,this study has specific quantitative improvements in terms of convergence speed,tracking accuracy or computational ***,the improved algorithm is further analyzed and carried out by using Yuankuan Energy’s ModelingTech semi-physical simulation *** results verify the feasibility and effectiveness of the improved algorithm in the offshore wind-solar hybrid power generation system.

关键词： Offshore wind power generation efficiency maximum power point tracking(MPPT) integral sliding mode control grey wolf optimization algorithm offshore photovoltaic cells

来源：评论

学校读者我要写书评

暂无评论

A Novel Self-Supervised Learning Network for Binocular Disparity Estimation

引用

computer Modeling in engineering & sciences 2025年第1期142卷 209-229页

作者： Jiawei Tian Yu Zhou Xiaobing Chen Salman A.AlQahtani Hongrong Chen Bo Yang Siyu Lu Wenfeng Zheng Department of Computer Science and Engineering Major in Bio Artificial IntelligenceHanyang UniversityAnsan-si15577Republic of Korea School of Electrical and Computer Engineering Louisiana State UniversityBaton RougeLA 70803USA Department of Computer Engineering College of Computer and Information SciencesKing Saud UniversityRiyadh11574Saudi Arabia School of Automation University of Electronic Science and Technology of ChinaChengdu610054China

Two-dimensional endoscopic images are susceptible to interferences such as specular reflections and monotonous texture illumination,hindering accurate three-dimensional lesion reconstruction by surgical *** study proposes a novel end-to-end disparity estimation model to address these *** approach combines a Pseudo-Siamese neural network architecture with pyramid dilated convolutions,integrating multi-scale image information to enhance robustness against lighting *** study introduces a Pseudo-Siamese structure-based disparity regression model that simplifies left-right image comparison,improving accuracy and *** model was evaluated using a dataset of stereo endoscopic videos captured by the Da Vinci surgical robot,comprising simulated silicone heart sequences and real heart video *** results demonstrate significant improvement in the network’s resistance to lighting interference without substantially increasing ***,the model exhibited faster convergence during training,contributing to overall performance *** study advances endoscopic image processing accuracy and has potential implications for surgical robot applications in complex environments.

关键词： Parallax estimation parallax regression model self-supervised learning Pseudo-Siamese neural network pyramid dilated convolution binocular disparity estimation

来源：评论

学校读者我要写书评

暂无评论

CNN-based Plant Leaf Disease Identification and Classification for Sustainable Agriculture 6

CNN-based Plant Leaf Disease Identification and Classificati...

引用

6th International Conference on Mobile Computing and Sustainable Informatics, ICMCSI 2025

作者： Srilatha, A. Praveen, P. School of Computer Science & Artificial Intelligence SR University Warangal506371 India

ISBN: (纸本)9798331522667

The rapid spread of leaf-diseases among the large-scale crops or plants will pose a great risk to the agricultural output and crop yield. Earlier detection and proper analysis of foliar disorders are essential for minimizing yield losses as well as forwarding continuous farming trials. This research presents a novel way to find and analyze leaf diseases using various deep learning algorithms. The proposed approach integrates Convolutional Neural Networks (CNN) in feature extraction for automatically identifying disease patterns from leaf-based images with high accuracy to exploit manual inspection of plant leaves. To achieve higher accuracy, this model is train and tested on a wide variety from diseased & healthy leaf images. This approach surpasses traditional image processing methods, exhibiting high precision and recall in identifying various disease types across multiple crops. The deep learning-based solution offers a scalable, efficient, and reliable tool for farmers and agricultural experts, potentially revolutionizing plant disease management strategies. In addition, it can expand the dataset and enhance real-time detection ability which probably could be applied into user-friendly mobile applications in future work. © 2025 IEEE.

关键词： Accuracy CNN Deep learning Image Classification leaf disease detection

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：