期刊文献+
任意字段
题名或关键词
题名
关键词
摘要
作者
第一作者
机构
刊名
分类号
参考文献
作者简介
基金资助
栏目信息
共找到6篇文章
< 1 >
每页显示 20 50 100
已选0条
引用分析
参考文献
引证文献
 统计分析
检索结果
已选文献
显示方式：
Attentive Neighborhood Feature Augmentation for Semi-supervised Learning 认领 引用
1
作者 Qi Liu Jing Li +1 位作者 Xianmin Wang Wenpeng Zhao 《Intelligent Automation & Soft Computing》 SCIE 2023年第8期1753-1771,共19页
Recent state-of-the-art semi-supervised learning(SSL)methods usually use data augmentations as core components.Such methods,however,are limited to simple transformations such as the augmentations under the instance’s... Recent state-of-the-art semi-supervised learning(SSL)methods usually use data augmentations as core components.Such methods,however,are limited to simple transformations such as the augmentations under the instance’s naive representations or the augmentations under the instance’s semantic representations.To tackle this problem,we offer a unique insight into data augmentations and propose a novel data-augmentation-based semi-supervised learning method,called Attentive Neighborhood Feature Aug-mentation(ANFA).The motivation of our method lies in the observation that the relationship between the given feature and its neighborhood may contribute to constructing more reliable transformations for the data,and further facilitating the classifier to distinguish the ambiguous features from the low-dense regions.Specially,we first project the labeled and unlabeled data points into an embedding space and then construct a neighbor graph that serves as a similarity measure based on the similar representations in the embedding space.Then,we employ an attention mechanism to transform the target features into augmented ones based on the neighbor graph.Finally,we formulate a novel semi-supervised loss by encouraging the predictions of the interpolations of augmented features to be consistent with the corresponding interpolations of the predictions of the target features.We carried out exper-iments on SVHN and CIFAR-10 benchmark datasets and the experimental results demonstrate that our method outperforms the state-of-the-art methods when the number of labeled examples is limited. 展开更多
关键词 Semi-supervised learning attention mechanism feature augmentation consistency regularization
暂未订购 下载PDF
Decentralized Semi-Supervised Learning for Stochastic Configuration Networks Based on the Mean Teacher Method 认领 引用
2
作者 Kaijing Li Wu Ai 《Journal of Computer and Communications》 2024年第4期247-261,共15页
The aim of this paper is to broaden the application of Stochastic Configuration Network (SCN) in the semi-supervised domain by utilizing common unlabeled data in daily life. It can enhance the classification accuracy ... The aim of this paper is to broaden the application of Stochastic Configuration Network (SCN) in the semi-supervised domain by utilizing common unlabeled data in daily life. It can enhance the classification accuracy of decentralized SCN algorithms while effectively protecting user privacy. To this end, we propose a decentralized semi-supervised learning algorithm for SCN, called DMT-SCN, which introduces teacher and student models by combining the idea of consistency regularization to improve the response speed of model iterations. In order to reduce the possible negative impact of unsupervised data on the model, we purposely change the way of adding noise to the unlabeled data. Simulation results show that the algorithm can effectively utilize unlabeled data to improve the classification accuracy of SCN training and is robust under different ground simulation environments. 展开更多
关键词 Stochastic Neural Network Consistency Regularization Semi-Supervised Learning Decentralized Learning
暂未订购 下载PDF
A New Kind of Conjugate-nested Central Configurations in Consisted of One Regular Tetrahedron and One Regular Octahedron 认领 引用 被引量：1
3
作者 LIU Xue-fei XIANG Yi-hua 《Chinese Quarterly Journal of Mathematics》 北大核心 2008年第2期309-316,共8页
A new case configuration in R^3, the conjugate-nest consisted of one regular tetrahedron and one regular octahedron is discussed. If the configuration is a central configuration, then all masses of outside layer are e... A new case configuration in R^3, the conjugate-nest consisted of one regular tetrahedron and one regular octahedron is discussed. If the configuration is a central configuration, then all masses of outside layer are equivalent, the masses of inside layer are also equivalent. At the same time the following relation between ρ（r =√3/3ρ is the radius ratio of the sizes） and mass ratio τ=~↑m/m must be satisfied τ=~↑m/m=ρ（ρ＋3）（3＋2ρ＋ρ^2）^-3/2＋ρ（-ρ＋3）（3-2ρ＋ρ^2）^-3/2-4.2^-3/2ρ^-2-^-1ρ^-2/2（1＋ρ）（3＋2ρ＋ρ^2）^-3/2＋2（ρ-1）（3-2ρ＋ρ^2）^-3/2-4（2√2）^-3ρ, and for any mass ratio τ, when mass ratio r is in the open interval （0, 0.03871633950 ... ）, there exist three central configuration solutions（the initial configuration conditions who imply hamagraphic solutions） corresponding radius ratios are r1, r2, and r3, two of them in the interval （2.639300779… , ＋∞） and one is in the interval （0.7379549890…, 1.490942703… ）. when mass ratio τ is in the open interval （130.8164950… , ＋∞）, in the same way there have three corresponding radius ratios, two of them in the interval （0, 0.4211584789... ） and one is in the interval （0.7379549890…, 1.490942703…）. When mass ratio τ is in the open interval （0.03871633950…, 130.8164950…）, there has only one solution r in the interval （0.7379549890…, 1.490942703… ）. 展开更多
关键词 N-body problems conjugate-nest consisted of one regular tetrahedron and one regular octahedron central configurations existence and uniqueness
暂未订购 下载PDF
PriorsMatch:prior-level pseudo-labels for semi-supervised object detection on medical images 认领 引用
4
作者 Jiaqiang CHEN Lei ZHANG +3 位作者 Wenjie LIU Xin WEI Jiaqi LI Xian JIANG 《Frontiers of Computer Science》 SCIE EI CAS CSCD 2026年第6期171-173,共3页
1 Introduction Object detection in medical imaging is vital for lesion identification but faces accuracy challenges due to scarce annotated data.Deep learning-based detectors need extensive labeled data,yet medical im... 1 Introduction Object detection in medical imaging is vital for lesion identification but faces accuracy challenges due to scarce annotated data.Deep learning-based detectors need extensive labeled data,yet medical image annotation is labor-intensive and time-consuming[1].Semi supervised object detection(SSOD)addresses this by leveraging unlabeled data to boost performance.Recent SSOD advancements integrate consistency regularization and pseudo-labeling within the MeanTeacher framework,where a teacher model generates pseudo labels from weakly augmented unlabeled data,and the student model is trained on strongly augmented versions.This enforces consistency in predictions,improving generalization.However,in medical imaging,where annotated data is scarce,these methods perform poorly compared to natural image applications. 展开更多
关键词 meanteacher frameworkwhere labeled datayet medical image leveraging unlabeled data object detection teacher model g consistency regularization supervised object detection ssod addresses
暂未订购 下载PDF
HAGAN:Hybrid Augmented Generative Adversarial Network for Medical Image Synthesis 认领 引用
5
作者 Zhihan Ju Wanting Zhou +4 位作者 Longteng Kong Yu Chen Yi Li Zhenan Sun Caifeng Shan 《Machine Intelligence Research》 EI CSCD 2025年第5期969-982,共14页
Medical image synthesis(MIS)can greatly save the economic and time costs of medical diagnosis.However,due to the complexity of medical images and similar characteristics of different tissue cells,existing methods face... Medical image synthesis(MIS)can greatly save the economic and time costs of medical diagnosis.However,due to the complexity of medical images and similar characteristics of different tissue cells,existing methods face great challenges in meeting their biological consistency.To this end,we propose the hybrid augmented generative adversarial network(HAGAN)to maintain the authenticity of structural texture and tissue cells.HAGAN contains attention mixed(AttnMix)generator,hierarchical discriminator and reverse skip connection between discriminator and generator.The AttnMix consistency differentiable regularization encourages the perception in structural and textural variations between real and fake images,which improves the pathological integrity of synthetic images and the accuracy of features in local areas.The hierarchical discriminator introduces pixel-by-pixel discriminant feedback to generator for enhancing the saliency and discriminance of global and local details simultaneously.The reverse skip connection further improves the accuracy for fine details by fusing real and synthetic distribution features.Our experimental evaluations on two datasets of different scales,i.e.,ACDC and BraTS2018,demonstrate that HAGAN outperforms the existing methods and achieves state-of-the-art performance in both high-resolution and low-resolution. 展开更多
关键词 Medical image synthesis generative adversarial network hybrid augmentation consistency differentiable regularization localdiscrimination
A Deep Model for Partial Multi-label Image Classification with Curriculum-based Disambiguation 认领 引用
6
作者 Feng Sun Ming-Kun Xie Sheng-Jun Huang 《Machine Intelligence Research》 EI CSCD 2024年第4期801-814,共14页
In this paper,we study the partial multi-label(PML)image classification problem,where each image is annotated with a candidate label set consisting of multiple relevant labels and other noisy labels.Existing PML metho... In this paper,we study the partial multi-label(PML)image classification problem,where each image is annotated with a candidate label set consisting of multiple relevant labels and other noisy labels.Existing PML methods typically design a disambiguation strategy to filter out noisy labels by utilizing prior knowledge with extra assumptions,which unfortunately is unavailable in many real tasks.Furthermore,because the objective function for disambiguation is usually elaborately designed on the whole training set,it can hardly be optimized in a deep model with stochastic gradient descent(SGD)on mini-batches.In this paper,for the first time,we propose a deep model for PML to enhance the representation and discrimination ability.On the one hand,we propose a novel curriculum-based disambiguation strategy to progressively identify ground-truth labels by incorporating the varied difficulties of different classes.On the other hand,consistency regularization is introduced for model training to balance fitting identified easy labels and exploiting potential relevant labels.Extensive experimental results on the commonly used benchmark datasets show that the proposed method significantlyoutperforms the SOTA methods. 展开更多
关键词 Partial multi-label image classification curriculum-based disambiguation consistency regularization label difficulty candidatelabel set.
已选0条
引用分析
参考文献
引证文献
 统计分析
检索结果
已选文献
上一页 1 下一页 到第 页
在线咨询 使用帮助 返回顶部 意见反馈