检索结果-内蒙古大学图书馆

Interactive prototype learning and self-learning for few-shot medical image segmentation

Artificial intelligence in medicine 2025年 167卷

作者： Yuhui Song Chenchu Xu Boyan Wang Xiuquan Du Jie Chen Yanping Zhang Shuo Li School of Computer Science and Technology Anhui University 230601 Hefei China Key Laboratory of Intelligent Computing and Signal Processing of Ministry of Education Anhui University 230601 Hefei China. Key Laboratory of Intelligent Computing and Signal Processing of Ministry of Education Anhui University 230601 Hefei China Institute of Artificial Intelligence Hefei Comprehensive National Science Center 230051 Hefei China. Electronic address: cxu332@***. Department of Computer Science and Technology Tsinghua University 100084 Beijing China. Electronic address: wby000000@***. School of Engineering Case Western Reserve University 44106 Cleveland United States.

Few-shot learning alleviates the heavy dependence of medical image segmentation on large-scale labeled data, but it shows strong performance gaps when dealing with new tasks compared with traditional deep learning. Existing methods mainly learn the class knowledge of a few known (support) samples and extend it to unknown (query) samples. However, the large distribution differences between the support image and the query image lead to serious deviations in the transfer of class knowledge, which can be specifically summarized as two segmentation challenges: Intra-class inconsistency and Inter-class similarity, blurred and confused boundaries. In this paper, we propose a new interactive prototype learning and self-learning network to solve the above challenges. First, we propose a deep encoding-decoding module to learn the high-level features of the support and query images to build peak prototypes with the greatest semantic information and provide semantic guidance for segmentation. Then, we propose an interactive prototype learning module to improve intra-class feature consistency and reduce inter-class feature similarity by conducting mid-level features-based mean prototype interaction and high-level features-based peak prototype interaction. Last, we propose a query features-guided self-learning module to separate foreground and background at the feature level and combine low-level feature maps to complement boundary information. Our model achieves competitive segmentation performance on benchmark datasets and shows substantial improvement in generalization ability.

关键词： Few-shot segmentation Medical image segmentation Prototype learning Self-learning

来源：评论

学校读者我要写书评

暂无评论

3R: Word and Phoneme Edition based Data Augmentation for Lexical Punctuation Prediction

3R: Word and Phoneme Edition based Data Augmentation for Lex...

引用

International Conference on computational intelligence and Security

作者： Aihua Zheng Naipeng Ye Xiao Wang Xiao Song Key Lab of Intelligent Computing and Signal Processing of Ministry of Education Hefei China Peking University Shenzhen Institute Shenzhen China Anhui Provincial Key Laboratory of Multimodal Cognitive Computation School of Computer Science and Technology Anhui University Hefei China

Existing Lexical Punctuation Prediction methods are mainly trained on the standard clean data while losing the generalization in practical automatic speech recognition (ASR) system with ubiquitous transcription errors. To bridge the gap between clean training data and noisy testing data, we propose three random (3R) data augmentation strategies: random word deletion (RWD), random word substitution (RWS), and random phoneme edition (RPE) in both word and phoneme levels on the training dataset. Specifically, we contribute an acoustically similar vocabulary with phoneme level editions for acoustically similar word substitution. In addition, we first introduce the RoBERTa-large model into a punctuation prediction task to capture the semantics and the long-distance dependencies in language. Extensive experiments on the English dataset IWSLT2011 yield to a new state-of-the-art comparing to the prevalent punctuation prediction methods.

关键词： Training Vocabulary Semantics Training data Predictive models Noise measurement Security

来源：评论

学校读者我要写书评

暂无评论

MSCIAIG-Net: Multi-scale spatial-channel interactive attention and interpretable guidance for fine-grained ship classification and visual inference network in remote sensing images

引用

Engineering Applications of Artificial intelligence 2025年 157卷

作者： Chengqiang Zhao Shijie Chen Jiashu Zhang Sichuan Province Key Laboratory of Signal and Information Processing Southwest Jiaotong University Chengdu 611756 China School of Information Science and Technology Southwest Jiaotong University Chengdu 611756 China School of Engineering and Physics Science Heriot-Watt University Edinburgh EH144AS UK School of Computing and Artificial Intelligence Southwest Jiaotong University Chengdu 611756 China

Fine-grained ship classification (FGSC) in remote sensing images (RSI) with high visual similarity is becoming increasingly important in civil and military applications involving ship monitoring. Existing studies predominantly seek to enhance the accuracy of classification and recognition of artificial intelligence models only by designing deep network structures or algorithms, which often extract redundant information containing much background noise, ultimately degrading the robustness of the fine-tuned model. We provide a multi-scale spatial-channel interactive attention and interpretable guidance network (MSCIAIG-Net) for FGSC in RSI. This is the first study to understand and address the issue of robustness degradation resulting from parameter redundancy in FGSC models for RSI through visualized attributions. Specifically, a multi-scale spatial channel interactive attention module (MSCIAM) is designed to model and interact with the importance between multi-scale spatial and channel features. Under the guidance of interpretability, a novel fine-grained classification loss with visual interpretation is developed, which strengthens the network's ability to learn discriminative feature representations in salient regions. Additionally, an interpretability-analysis-based network pruning (IANP) strategy is introduced to reduce the noise and redundant information from the network, thereby achieving model compression and performance enhancement within a certain range without sacrificing accuracy. Furthermore, performance verification is implemented on the public dataset, Fine-grained Ship Collection-23 (FGSC-23), and our collated dataset, and MSCIAIG-Net attains the competitive accuracy and interpretability under identical conditions. Notably, for MSCIAIG-Net with Residual Network 50 Layers as the backbone network verified on FGSC-23, its overall accuracy ( OA ) and average accuracy ( AA ) improves by 6.79 % and 5.54 %, respectively.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Let's play music: Audio-driven performance video generation

arXiv

引用

arXiv 2020年

作者： Zhu, Hao Li, Yi Zhu, Feixia Zheng, Aihua He, Ran Key Laboratory of Intelligent Computing and Signal Processing of Ministry of Education School of Computer Science and Technology Anhui University Hefei China CASIA Beijing China School of Artificial Intelligence University of Chinese Academy of Sciences Beijing China Center for Excellence in Brain Science and Intelligence Technology CAS Beijing China

We propose a new task named Audio-driven Performance Video Generation (APVG), which aims to synthesize the video of a person playing a certain instrument guided by a given music audio clip. It is a challenging task to generate the high-dimensional temporal consistent videos from low-dimensional audio modality. In this paper, we propose a multistaged framework to achieve this new task to generate realistic and synchronized performance video from given music. Firstly, we provide both global appearance and local spatial information by generating the coarse videos and keypoints of body and hands from a given music respectively. Then, we propose to transform the generated keypoints to heatmap via a differentiable space transformer, since the heatmap offers more spatial information but is harder to generate directly from audio. Finally, we propose a Structured Temporal UNet (STU) to extract both intra-frame structured information and inter-frame temporal consistency. They are obtained via graph-based structure module, and CNN-GRU based high-level temporal module respectively for final video generation. Comprehensive experiments validate the effectiveness of our proposed framework. Copyright © 2020, The Authors. All rights reserved.

关键词： Music

来源：评论

学校读者我要写书评

暂无评论

Two-Stream Graph Convolutional Network for Intra-oral Scanner Image Segmentation

arXiv

引用

arXiv 2022年

作者： Zhao, Yue Zhang, Lingming Liu, Yang Meng, Deyu Cui, Zhiming Gao, Chenqiang Gao, Xinbo Lian, Chunfeng Shen, Dinggang Chongqing University of Posts and Telecommunications School of Communication and Information Engineering Chongqing400065 China The Chongqing Key Laboratory of Signal and Information Processing Chongqing400065 China Department of Orthodontics Stomatological Hospital of Chongqing Medical University Chongqing401147 China Chongqing Key Laboratory for Oral Diseases and Biomedical Sciences Chongqing401147 China Faculty of Information Technology Macau University of Science and Technology China School of Mathematics and Statistics Xi'an Jiaotong University Xian710049 China School of Biomedical Engineering ShanghaiTech University Shanghai201210 China Shanghai United Imaging Intelligence Co. Ltd. Shanghai200030 China The School of Computer Science The University of Hong Kong 999077 Hong Kong School of Computer Science and Technology Chongqing University of Posts and Telecommunications Chongqing400065 China

Precise segmentation of teeth from intra-oral scanner images is an essential task in computer-aided orthodontic surgical planning. The state-of-the-art deep learning-based methods often simply concatenate the raw geometric attributes (i.e., coordinates and normal vectors) of mesh cells to train a single-stream network for automatic intra-oral scanner image segmentation. However, since different raw attributes reveal completely different geometric information, the naive concatenation of different raw attributes at the (low-level) input stage may bring unnecessary confusion in describing and differentiating between mesh cells, thus hampering the learning of high-level geometric representations for the segmentation task. To address this issue, we design a two-stream graph convolutional network (i.e., TSGCN), which can effectively handle inter-view confusion between different raw attributes to more effectively fuse their complementary information and learn discriminative multi-view geometric representations. Specifically, our TSGCN adopts two input-specific graph-learning streams to extract complementary high-level geometric representations from coordinates and normal vectors, respectively. Then, these single-view representations are further fused by a self-attention module to adaptively balance the contributions of different views in learning more discriminative multi-view representations for accurate and fully automatic tooth segmentation. We have evaluated our TSGCN on a real-patient dataset of dental (mesh) models acquired by 3D intraoral scanners. Experimental results show that our TSGCN significantly outperforms state-of-the-art methods in 3D tooth (surface) segmentation. Github: https://***/ZhangLingMing1/TSGCNet. © 2022, CC BY.

关键词： Scanning

来源：评论

学校读者我要写书评

暂无评论

Multi-Category Fusion Contrastive Learning with Core Data Selection for Robust RGB Image-based Dental Caries Classification

引用

Information Fusion 2025年 124卷

作者： Peiliang Zhang Yaru Chen Yunjiong Liu Chao Che Yongjun Zhu Key Laboratory of Advanced Design and Intelligent Computing (Dalian University) Ministry of Education Dalian 116622 China School of Computer Science and Artificial Intelligence Wuhan University of Technology Wuhan 430070 China Department of Library and Information Science Yonsei University Seoul 03722 Republic of Korea Centre for Vision Speech and Signal Processing (CVSSP) University of Surrey Surrey GU2 7NA United Kingdom School of Software Engineering Dalian University Dalian 116622 China

Dental caries represents one of the most prevalent diseases affecting humankind, particularly among adolescent populations. RGB images offer a convenient and cost-effective method for dental caries detection. However, the image data captured may suffer from blurriness, which, together with label errors introduced during manual annotations, can degrade the performance of the model learned for dental caries detection. To address this problem, we propose the Multi-Category Fusion Contrastive Learning with Core Data Selection (M3C) to improve the predictive performance of dental caries classification models. Instead of fine-tuning the backbone network structure, M3C focuses on improving the robustness of model to label errors from a novel perspective by identifying core data that is highly relevant to the dental caries category. We analyzed and validated that M3C has better robustness in dental caries detection from model architecture representation, theoretical analysis, and mutual information computation. Specifically, M3C quantifies the average mutual information between dental caries images and dental caries category centers based on Jensen-Shannon Divergence (JSD), which is then used for selecting the core data to mitigate the impact of label errors on model performance. Furthermore, we design inter-category contrastive learning to enhance the performance of the model in distinguishing the categories of dental caries by improving the feature representation for samples of different categories. With theoretical justification, we jointly optimized model training using prediction loss and confusion contrastive loss. Extensive experiments demonstrate that M3C significantly surpasses comparative data selection methods in dental caries detection on dental caries RGB image datasets. More excitingly, M3C achieves superior predictive performance using only 50% of the core data compared to state-of-the-art dental caries detection methods using the entire dataset. Our code is

关键词：

来源：评论

学校读者我要写书评

暂无评论

New Framework for Code-Mapping-based Reversible Data Hiding in JPEG Images

arXiv

引用

arXiv 2020年

作者： Du, Yang Yin, Zhaoxia Key Lab of Intelligent Computing and Signal Processing of Ministry of Education School of Computer Science and Technology Anhui University Hefei230601 China Anhui Key Laboratory of Multimodal Cognitive Computation School of Computer Science and Technology Anhui University Hefei230601 China School of Communication & Electronic Engineering East China Normal University Shanghai200241 China

Code mapping (CM) is an efficient technique for reversible data hiding (RDH) in JPEG images, which embeds data by constructing a mapping relationship between the used and unused codes in the JPEG bitstream. This study presents a new framework for designing a CM-based RDH method. First, a new code mapping strategy is proposed to suppress file size expansion and improve applicability. Based on our proposed strategy, the mapped codes are redefined by creating a new Huffman table rather than selecting them from the unused codes in the original Huffman table. The critical issue of designing the CM-based RDH method, that is, constructing code mapping, is converted into a combinatorial optimization problem. This study proposes a novel CM-based RDH method that utilizes a genetic algorithm (GA). The experimental results demonstrate that the proposed method achieves a high embedding capacity with no signal distortion while suppressing file size expansion. Copyright © 2020, The Authors. All rights reserved.

关键词： Mapping

来源：评论

学校读者我要写书评

暂无评论

Correction to: Enhancing cyber defense strategies with discrete multi-dimensional Z-numbers: a multi-attribute decision-making approach

引用

Complex & Intelligent Systems 2025年第7期11卷 1-1页

作者： Yao, Aiting Huang, Chen Zhang, Weiqi Dong, Chengzu Lu, Meiqu Mao, Junjun Liu, Xiao Li, Xuejun Anhui Provincial International Joint Research Center for Advanced Technology in Medical Imaging School of Computer Science and Technology Anhui University Hefei China AI Techplus Pty Ltd Organization Melbourne Australia School of Information Technology Deakin University Geelong Australia School of Data Science Lingnan University Hongkong China School of Artificial Intelligence Guangxi Minzu University Nanning China Key Laboratory of Intelligent Computing and Signal Processing Ministry of Education Hefei China

来源：评论

学校读者我要写书评

暂无评论

Evolving multi-resolution pooling CNN for monaural singing voice separation

arXiv

引用

arXiv 2020年

作者： Yuan, Weitao Dong, Bofei Wang, Shengbei Unoki, Masashi Wang, Wenwu Tianjin Key Laboratory of Autonomous Intelligence Technology and Systems School of Computer Science and Technology Tianjin Polytechnic University Tianjin China School of Information Science Japan Advanced Institute of Science and Technology Japan Centre for Vision Speech and Signal Processing University of Surrey Guildford United Kingdom

Monaural Singing Voice Separation (MSVS) is a challenging task and has been studied for decades. Deep neural networks (DNNs) are the current state-of-the-art methods for MSVS. However, the existing DNNs are often designed manually, which is time-consuming and error-prone. In addition, the network architectures are usually pre-defined, and not adapted to the training data. To address these issues, we introduce a Neural Architecture Search (NAS) method to the structure design of DNNs for MSVS. Specifically, we propose a new multi-resolution Convolutional Neural Network (CNN) framework for MSVS namely Multi-Resolution Pooling CNN (MRP-CNN), which uses various-size pooling operators to extract multi-resolution features. Based on the NAS, we then develop an evolving framework namely Evolving MRP-CNN (E-MRP-CNN), by automatically searching the effective MRP-CNN structures using genetic algorithms, optimized in terms of a single-objective considering only separation performance, or multi-objective considering both the separation performance and the model complexity. The multiobjective E-MRP-CNN gives a set of Pareto-optimal solutions, each providing a trade-off between separation performance and model complexity. Quantitative and qualitative evaluations on the MIR-1K and DSD100 datasets are used to demonstrate the advantages of the proposed framework over several recent baselines. Copyright © 2020, The Authors. All rights reserved.

关键词： Deep neural networks

来源：评论

学校读者我要写书评

暂无评论

Self-grouping convolutional neural networks

arXiv

引用

arXiv 2020年

作者： Guo, Qingbei Wu, Xiao-Jun Kittler, Josef Feng, Zhiquan Jiangsu Provincial Engineering Laboratory of Pattern Recognition and Computational Intelligence Jiangnan University Wuxi214122 China Shandong Provincial Key Laboratory of Network based Intelligent Computing University of Jinan Jinan250022 China Centre for Vision Speech and Signal Processing University of Surrey GuildfordGU2 7XH United Kingdom

Although group convolution operators are increasingly used in deep convolutional neural networks to improve the computational efficiency and to reduce the number of parameters, most existing methods construct their group convolution architectures by a predefined partitioning of the filters of each convolutional layer into multiple regular filter groups with an equal spatial group size and data-independence, which prevents a full exploitation of their potential. To tackle this issue, we propose a novel method of designing self-grouping convolutional neural networks, called SG-CNN, in which the filters of each convolutional layer group themselves based on the similarity of their importance vectors. Concretely, for each filter, we first evaluate the importance value of their input channels to identify the importance vectors, and then group these vectors by clustering. Using the resulting data-dependent centroids, we prune the less important connections, which implicitly minimizes the accuracy loss of the pruning, thus yielding a set of diverse group convolution filters. Subsequently, we develop two fine-tuning schemes, i.e. (1) both local and global fine-tuning and (2) global only fine-tuning, which experimentally deliver comparable results, to recover the recognition capacity of the pruned network. Comprehensive experiments carried out on the CIFAR-10/100 and ImageNet datasets demonstrate that our self-grouping convolution method adapts to various state-of-the-art CNN architectures, (Figure presented) Figure 1: Evolution of group convolutions. (a) Regular convolution. (b) Regular group convolution. (c) Permuting group convolution. (d) Learned group convolution. (d) Self-grouping convolution. Note that white channels represent the ignored input channels, and gray channels indicate the reused input channels. such as ResNet and DenseNet, and delivers superior performance in terms of compression ratio, speedup and recognition accuracy. We demonstrate the ability of SG-CNN

关键词： Convolution

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：