检索结果-南通市图书馆

few-shot learning for Named Entity Recognition Based on BERT and Two-level Model Fusion

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Data Intelligence 2021年第4期3卷 568-577页

作者： Yuan Gong Lu Mao Changliang Li AI Lab King Soft CorporationBeijing 100086China

Currently,as a basic task of military document information extraction,Named Entity Recognition(NER)for military documents has received great *** 2020,China Conference on Knowledge Graph and Semantic Computing(CCKS)and System Engineering Research Institute of Academy of Military Sciences(AMS)issued the NER task for test evaluation,which requires the recognition of four types of entities including Test Elements(TE),Performance Indicators(PI),System Components(SC)and Task Scenarios(TS).Due to the particularity and confidentiality of the military field,only 400 items of annotated data are provided by the *** this paper,the task is regarded as a few-shot learning problem for NER,and a method based on BERT and two-level model fusion is ***,the proposed method is based on several basic models fine tuned by BERT on the training ***,a two-level fusion strategy applied to the prediction results of multiple basic models is proposed to alleviate the over-fitting ***,the labeling errors are eliminated by *** method achieves F1 score of 0.7203 on the test set of the evaluation task.

关键词： few-shot learning Named entity recognition BERT Two-level model fusion

few-shot learning for biotic stress classification of coffee leaves

在线全文

学校读者我要写书评

暂无评论

Artificial Intelligence in Agriculture 2022年第1期6卷 55-67页

作者： Lucas M.Tassis Renato A.Krohling LABCIN-Nature Inspired Computing Lab Federal University of Espirito SantoAv.Fernando Ferrari514CEP29075-910 VitóriaEspırito SantoESBrazil PPGI-Graduate Program in Computer Science Federal University of Espirito SantoAv.Fernando Ferrari514CEP 29075-910VitóriaEspírito SantoESBrazil

In the last few years,deep neural networks have achieved promising results in several ***,one of the main limitations of these methods is the need for large-scale datasets to properly ***-shot learning methods emerged as an attempt to solve this *** the few-shot learning methods,there is a class of methods known as embedding learning or metric *** methods tackle the classification problem by learning to compare,needing fewer training *** of the main problems in plant diseases and pests recognition is the lack of large public datasets *** to this difficulty,the field emerges as an intriguing application to evaluate the few-shot learning *** field is also relevant due to the social and economic importance of agriculture in several *** this work,datasets consisting of biotic stresses in coffee leaves are used as a case study to evaluate the performance of few-shot learning in classification and severity estimation *** achieved competitive results compared with the ones reported in the literature in the classification task,with accuracy values close to 96%.Furthermore,we achieved superior results in the severity estimation task,obtaining 6.74%greater accuracy than the baseline.

关键词： Plant diseases and pests classification Image classification few-shot learning Meta-learning Convolutional neural networks

Saliency-guided meta-hallucinator for few-shot learning

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Science China(Information Sciences) 2024年第10期67卷 189-210页

作者： Hongguang ZHANG Chun LIU Jiandong WANG Linru MA Piotr KONIUSZ Philip H.S.TORR Lin YANG Systems Engineering Institute Academy of Military Sciences Data61 Commonwealth Scientific and Industrial Research Organisation Australian National University Oxford University

learning novel object concepts from limited samples remains a considerable challenge in deep learning. The main directions for improving the few-shot learning models include(i) designing a stronger backbone,(ii) designing a powerful(dynamic) meta-classifier, and(iii) using a larger pre-training set obtained by generating or hallucinating additional samples from the small scale dataset. In this paper, we focus on item(iii) and present a novel meta-hallucination strategy. Presently, most image generators are based on a generative network(i.e., GAN) that generates new samples from the captured distribution of images. However, such networks require numerous annotated samples for training. In contrast, we propose a novel saliency-based end-to-end meta-hallucinator, where a saliency detector produces foregrounds and backgrounds of support images. Such images are fed into a two-stream network to hallucinate feature samples directly in the feature space by mixing foreground and background feature samples. Then, we propose several novel mixing strategies that improve the quality and diversity of hallucinated feature ***, as not all saliency maps are meaningful or high quality, we further introduce a meta-hallucination controller that decides which foreground feature samples should participate in mixing with backgrounds. To our knowledge, we are the first to leverage saliency detection for few-shot learning. Our proposed network achieves state-of-the-art results on publicly available few-shot image classification and anomaly detection benchmarks, and outperforms competing sample mixing strategies such as the so-called Manifold Mixup.

关键词： few-shot learning saliency detection object recognition anomaly detection computer vision

同方期刊数据库

Recent advances of few-shot learning methods and applications

在线全文

学校读者我要写书评

暂无评论

Science China(Technological Sciences) 2023年第4期66卷 920-944页

作者： WANG JianYuan LIU KeXin ZHANG YuCheng LENG Biao LU JinHu School of Automation Science and Electrical Engineering Beihang UniversityBeijing 100191China School of Computer Science and Engineering Beihang UniversityBeijing 100191China

The rapid development of deep learning provides great convenience for production and ***,the massive labels required for training models limits further ***-shot learning which can obtain a high-performance model by learning few samples in new tasks,providing a solution for many scenarios that lack *** paper summarizes few-shot learning algorithms in recent years and proposes a ***,we introduce the few-shot learning task and its ***,according to different implementation strategies,few-shot learning methods in recent years are divided into five categories,including data augmentation-based methods,metric learning-based methods,parameter optimization-based methods,external memory-based methods,and other ***,We investigate the application of few-shot learning methods and summarize them from three directions,including computer vision,human-machine language interaction,and robot ***,we analyze the existing few-shot learning methods by comparing evaluation results on mini Image Net,and summarize the whole paper.

关键词： few-shot learning deep learning meta learning data augmentation parameter optimization

Sparse spatial transformers for few-shot learning

在线全文

学校读者我要写书评

暂无评论

Science China(Information Sciences) 2023年第11期66卷 23-34页

作者： Haoxing CHEN Huaxiong LI Yaohui LI Chunlin CHEN Department of Control Science and Intelligence Engineering Nanjing University

learning from limited data is challenging because data scarcity leads to a poor generalization of the trained model. A classical global pooled representation will probably lose useful local *** few-shot learning methods have recently addressed this challenge using deep descriptors and learning a pixel-level metric. However, using deep descriptors as feature representations may lose image contextual information. Moreover, most of these methods independently address each class in the support set, which cannot sufficiently use discriminative information and task-specific embeddings. In this paper, we propose a novel transformer-based neural network architecture called sparse spatial transformers(SSFormers), which finds task-relevant features and suppresses task-irrelevant features. Particularly, we first divide each input image into several image patches of different sizes to obtain dense local features. These features retain contextual information while expressing local information. Then, a sparse spatial transformer layer is proposed to find spatial correspondence between the query image and the full support set to select task-relevant image patches and suppress task-irrelevant image patches. Finally, we propose using an image patch-matching module to calculate the distance between dense local representations, thus determining which category the query image belongs to in the support set. Extensive experiments on popular few-shot learning benchmarks demonstrate the superiority of our method over state-of-the-art methods.

关键词： few-shot learning transformer metric-learning cross-attention

Meta-BN Net for few-shot learning

在线全文

同方期刊数据库

学校读者我要写书评

暂无评论

Frontiers of Computer Science 2023年第1期17卷 73-80页

作者： Wei GAO Mingwen SHAO Jun SHU Xinkai ZHUANG School of Computer Science China University of PetroleumQingdao 266580China School of Mathematics and Statistics Xi’an Jiaotong UniversityXi’an 710049China

In this paper, we propose a lightweight network with an adaptive batch normalization module, called Meta-BN Net, for few-shot classification. Unlike existing few-shot learning methods, which consist of complex models or algorithms, our approach extends batch normalization, an essential part of current deep neural network training, whose potential has not been fully explored. In particular, a meta-module is introduced to learn to generate more powerful affine transformation parameters, known as and , in the batch normalization layer adaptively so that the representation ability of batch normalization can be activated. The experimental results on miniImageNet demonstrate that Meta-BN Net not only outperforms the baseline methods at a large margin but also is competitive with recent state-of-the-art few-shot learning methods. We also conduct experiments on fewshot-CIFAR100 and CUB datasets, and the results show that our approach is effective to boost the performance of weak baseline networks. We believe our findings can motivate to explore the undiscovered capacity of base components in a neural network as well as more efficient few-shot learning methods.

关键词： meta-learning few-shot learning batch normalization

Automated Classification of Inherited Retinal Diseases in Optical Coherence Tomography Images Using few-shot learning

在线全文

学校读者我要写书评

暂无评论

Biomedical and Environmental Sciences 2023年第5期36卷 431-440页

作者： ZHAO Qi MAI Si Wei LI Qian HUANG Guan Chong GAO Ming Chen YANG Wen Li WANG Ge MA Ya LI Lei PENG Xiao Yan Department of Ophthalmology Beijing Tongren Eye CenterBeijing Tongren HospitalCapital Medical UniversityBeijing Key Laboratory of Ophthalmology and Visual SciencesBeijing 100730China Department of Computer Science RutgersThe State University of New JerseyNew Brunswick 08901USA Department of Computer Science and Engineering University at BuffaloBuffalo 14260USA Beijing Institute of Ophthalmology Beijing Tongren HospitalCapital Medical UniversityBeijing Ophthalmology and Visual Science KeyLaboratoryBeijing 100730China

Objective To develop a few-shot learning(FSL) approach for classifying optical coherence tomography(OCT) images in patients with inherited retinal disorders(IRDs).Methods In this study, an FSL model based on a student–teacher learning framework was designed to classify images. 2,317 images from 189 participants were included. Of these, 1,126 images revealed IRDs, 533 were normal samples, and 658 were control *** The FSL model achieved a total accuracy of 0.974–0.983, total sensitivity of 0.934–0.957, total specificity of 0.984–0.990, and total F1 score of 0.935–0.957, which were superior to the total accuracy of the baseline model of 0.943–0.954, total sensitivity of 0.866–0.886, total specificity of 0.962–0.971,and total F1 score of 0.859–0.885. The performance of most subclassifications also exhibited advantages. Moreover, the FSL model had a higher area under curves(AUC) of the receiver operating characteristic(ROC) curves in most *** This study demonstrates the effective use of the FSL model for the classification of OCT images from patients with IRDs, normal, and control participants with a smaller volume of data. The general principle and similar network architectures can also be applied to other retinal diseases with a low prevalence.

关键词： few-shot learning Student-teacher learning Knowledge distillation Transfer learning Optical coherence tomography Retinal degeneration Inherited retinal diseases

A New Diagnosis Method with few-shot learning Based on a Class-rebalance Strategy for Scarce Faults in Industrial Processes

在线全文

学校读者我要写书评

暂无评论

Machine Intelligence Research 2023年第4期20卷 583-594页

作者： Xinyao Xu De Xu Fangbo Qin Research Center of Precision Sensing and Control Institute of AutomationChinese Academy of SciencesBeijing100190China School of Artificial Intelligence University of Chinese Academy of SciencesBeijing100049China

For industrial processes, new scarce faults are usually judged by experts. The lack of instances for these faults causes a severe data imbalance problem for a diagnosis model and leads to low performance. In this article, a new diagnosis method with few-shot learning based on a class-rebalance strategy is proposed to handle the problem. The proposed method is designed to transform instances of the different faults into a feature embedding space. In this way, the fault features can be transformed into separate feature clusters. The fault representations are calculated as the centers of feature clusters. The representations of new faults can also be effectively calculated with few support instances. Therefore, fault diagnosis can be achieved by estimating feature similarity between instances and faults. A cluster loss function is designed to enhance the feature clustering performance. Also, a class-rebalance strategy with data augmentation is designed to imitate potential faults with different reasons and degrees of severity to improve the model’s generalizability. It improves the diagnosis performance of the proposed method. Simulations of fault diagnosis with the proposed method were performed on the Tennessee-Eastman benchmark. The proposed method achieved average diagnosis accuracies ranging from 81.8% to 94.7% for the eight selected faults for the simulation settings of support instances ranging from 3 to 50. The simulation results verify the effectiveness of the proposed method.

关键词： Data augmentation feature clustering class-rebalance strategy few-shot learning fault diagnosis

Dynamic Analogical Association Algorithm Based on Manifold Matching for few-shot learning

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Computer Systems Science & Engineering 2023年第7期46卷 1233-1247页

作者： Yuncong Peng Xiaolin Qin Qianlei Wang Boyi Fu Yongxiang Gu Chengdu Institute of Computer Applications Chinese Academy of SciencesChengdu610041China University of Chinese Academy of Sciences Beijing100049China

At present,deep learning has been well applied in many ***,due to the high complexity of hypothesis space,numerous training samples are usually required to ensure the reliability of minimizing experience ***,training a classifier with a small number of training examples is a challenging *** a biological point of view,based on the assumption that rich prior knowledge and analogical association should enable human beings to quickly distinguish novel things from a few or even one example,we proposed a dynamic analogical association algorithm to make the model use only a few labeled samples for *** be specific,the algorithm search for knowledge structures similar to existing tasks in prior knowledge based on manifold matching,and combine sampling distributions to generate offsets instead of two sample points,thereby ensuring high confidence and significant contribution to the *** comparative results on two common benchmark datasets substantiate the superiority of the proposed method compared to existing data generation approaches for few-shot learning,and the effectiveness of the algorithm has been proved through ablation experiments.

关键词： few-shot learning manifold matching analogical association data generation