您的检索:
学者姓名:贾熹滨
精炼检索结果:
年份
成果类型
收录类型
来源
综合
合作者
语言
清除所有精炼条件
摘要 :
金字塔原型对齐的轻量级小样本语义分割网络
关键词 :
原型对齐正则化 原型对齐正则化 卷积神经网络 卷积神经网络 轻量级网络 轻量级网络 小样本语义分割 小样本语义分割 多尺度 多尺度 金字塔池化 金字塔池化
引用:
复制并粘贴一种已设定好的引用格式,或利用其中一个链接导入到文献管理软件中。
GB/T 7714 | 贾熹滨 , 李佳 , 北京工业大学学报 . 金字塔原型对齐的轻量级小样本语义分割网络 [J]. | 贾熹滨 , 2021 , 47 (5) : 455-462,519 . |
MLA | 贾熹滨 等. "金字塔原型对齐的轻量级小样本语义分割网络" . | 贾熹滨 47 . 5 (2021) : 455-462,519 . |
APA | 贾熹滨 , 李佳 , 北京工业大学学报 . 金字塔原型对齐的轻量级小样本语义分割网络 . | 贾熹滨 , 2021 , 47 (5) , 455-462,519 . |
导入链接 | NoteExpress RIS BibTex |
摘要 :
小样本图像语义分割任务是计算机视觉领域一个有挑战性的问题,其目标是利用现有一张或几张带有密集分割注释的图片来预测未见类图像的分割掩码.针对该任务,提出了一个基于金字塔原型对齐的轻量级小样本图像语义分割网络.首先,该网络在MobileNetV2网络的深度可分离卷积和逆残差结构基础上,通过金字塔池化模块进行提取特征,保持高维度和低维度的信息,获得不同尺度的特征.同时通过在支持集原型和查询集之间进行相互对齐,使得网络能够从支持集中学到更多的信息,充分利用支持集的信息进行反馈.基于PASCAL-5~i数据集的大量实验结果表明,提出的网络结构的均值在1-way 1-shot和1-way 5-shot上分...
关键词 :
卷积神经网络 卷积神经网络 原型对齐正则化 原型对齐正则化 多尺度 多尺度 小样本语义分割 小样本语义分割 轻量级网络 轻量级网络 金字塔池化 金字塔池化
引用:
复制并粘贴一种已设定好的引用格式,或利用其中一个链接导入到文献管理软件中。
GB/T 7714 | 贾熹滨 , 李佳 . 金字塔原型对齐的轻量级小样本语义分割网络 [J]. | 北京工业大学学报 , 2021 , 47 (05) : 455-462,519 . |
MLA | 贾熹滨 等. "金字塔原型对齐的轻量级小样本语义分割网络" . | 北京工业大学学报 47 . 05 (2021) : 455-462,519 . |
APA | 贾熹滨 , 李佳 . 金字塔原型对齐的轻量级小样本语义分割网络 . | 北京工业大学学报 , 2021 , 47 (05) , 455-462,519 . |
导入链接 | NoteExpress RIS BibTex |
摘要 :
结合影像学和人工智能技术对病灶进行无创性定量分析是目前智慧医疗的一个重要研究方向.针对肝细胞癌(Hepatocellular carcinoma, HCC)分化程度的无创性定量估测方法研究,结合放射科医师的临床读片经验,提出了一种基于自注意力指导的多序列融合肝细胞癌组织学分化程度无创判别计算模型.以动态对比增强核磁共振成像(Dynamic contrastenhanced magnetic resonance imaging, DCE-MRI)的多个序列为输入,学习各时序序列及各序列的多层扫描切片在分化程度判别任务的权重,加权序列中具有的良好判别性能的时间和空间特征,以提升分化程度判别性能.模...
关键词 :
动态对比增强核磁共振成像 动态对比增强核磁共振成像 多序列融合 多序列融合 肝细胞癌分级 肝细胞癌分级 自注意力机制 自注意力机制 辅助诊断 辅助诊断
引用:
复制并粘贴一种已设定好的引用格式,或利用其中一个链接导入到文献管理软件中。
GB/T 7714 | 贾熹滨 , 孙政 , 杨大为 et al. 自注意力指导的多序列融合肝细胞癌分化判别模型 [J]. | 工程科学学报 , 2021 , 43 (09) : 1149-1156 . |
MLA | 贾熹滨 et al. "自注意力指导的多序列融合肝细胞癌分化判别模型" . | 工程科学学报 43 . 09 (2021) : 1149-1156 . |
APA | 贾熹滨 , 孙政 , 杨大为 , 杨正汉 . 自注意力指导的多序列融合肝细胞癌分化判别模型 . | 工程科学学报 , 2021 , 43 (09) , 1149-1156 . |
导入链接 | NoteExpress RIS BibTex |
摘要 :
Context: Training deep learning models for code readability classification requires large datasets of quality pre-labeled data. However, it is almost always time-consuming and expensive to acquire readability data with manual labels. Objective: We thus propose to introduce data augmentation approaches to artificially increase the size of training set, this is to reduce the risk of overfitting caused by the lack of readability data and further improve the classification accuracy as the ultimate goal. Method: We create transformed versions of code snippets by manipulating original data from aspects such as comments, indentations, and names of classes/methods/variables based on domain-specific knowledge. In addition to basic transformations, we also explore the use of Auxiliary Classifier GANs to produce synthetic data. Results: To evaluate the proposed approach, we conduct a set of experiments. The results show that the classification performance of deep neural networks can be significantly improved when they are trained on the augmented corpus, achieving a state-of-the-art accuracy of 87.38%. Conclusion: We consider the findings of this study as primary evidence of the effectiveness of data augmentation in the field of code readability classification.
关键词 :
Code readability classification Code readability classification Data augmentation Data augmentation Deep learning Deep learning Empirical software engineering Empirical software engineering Generative adversarial network Generative adversarial network
引用:
复制并粘贴一种已设定好的引用格式,或利用其中一个链接导入到文献管理软件中。
GB/T 7714 | Mi, Qing , Xiao, Yan , Cai, Zhi et al. The effectiveness of data augmentation in code readability classification [J]. | INFORMATION AND SOFTWARE TECHNOLOGY , 2021 , 129 . |
MLA | Mi, Qing et al. "The effectiveness of data augmentation in code readability classification" . | INFORMATION AND SOFTWARE TECHNOLOGY 129 (2021) . |
APA | Mi, Qing , Xiao, Yan , Cai, Zhi , Jia, Xibin . The effectiveness of data augmentation in code readability classification . | INFORMATION AND SOFTWARE TECHNOLOGY , 2021 , 129 . |
导入链接 | NoteExpress RIS BibTex |
摘要 :
One of the most common methods for diagnosing coronary artery disease is the use of the coronary artery calcium score CT. However, the current diagnostic method using the coronary artery calcium score CT requires a considerable time, because the radiologist must manually check the CT images one-by-one, and check the exact range. In this paper, three CNN models are applied for 1200 normal cardiovascular CT images, and 1200 CT images in which calcium is present in the cardiovascular system. We conduct the experimental test by classifying the CT image data into the original coronary artery calcium score CT images containing the entire rib cage, the cardiac segmented images that cut out only the heart region, and cardiac cropped images that are created by using the cardiac images that are segmented into nine sub-parts and enlarged. As a result of the experimental test to determine the presence of calcium in a given CT image using Inception Resnet v2, VGG, and Resnet 50 models, the highest accuracy of 98.52% was obtained when cardiac cropped image data was applied using the Resnet 50 model. Therefore, in this paper, it is expected that through further research, both the simple presence of calcium and the automation of the calcium analysis score for each coronary artery calcium score CT will become possible.
关键词 :
calcium detection calcium detection coronary artery calcium score CT coronary artery calcium score CT deep learning deep learning image classification image classification inception resnet V2 inception resnet V2 resnet-50 resnet-50 VGG VGG
引用:
复制并粘贴一种已设定好的引用格式,或利用其中一个链接导入到文献管理软件中。
GB/T 7714 | Lee, Sungjin , Rim, Beanbonyka , Jou, Sung-Shick et al. Deep-Learning-Based Coronary Artery Calcium Detection from CT Image [J]. | SENSORS , 2021 , 21 (21) . |
MLA | Lee, Sungjin et al. "Deep-Learning-Based Coronary Artery Calcium Detection from CT Image" . | SENSORS 21 . 21 (2021) . |
APA | Lee, Sungjin , Rim, Beanbonyka , Jou, Sung-Shick , Gil, Hyo-Wook , Jia, Xibin , Lee, Ahyoung et al. Deep-Learning-Based Coronary Artery Calcium Detection from CT Image . | SENSORS , 2021 , 21 (21) . |
导入链接 | NoteExpress RIS BibTex |
摘要 :
Unsupervised clustering is a kind of popular solution for unsupervised person re-identification (re-ID). However, due to the influence of cross-view differences, the results of clustering labels are not accurate. To solve this problem, an unsupervised re ID method based on cross-view distributed alignment (CV-DA) to reduce the influence of unsupervised cross-view is proposed. Specifically, based on a popular unsupervised clustering method, density clustering DBSCAN is used to obtain pseudo labels. By calculating the similarity scores of images in the target domain and the source domain, the similarity distribution of different camera views is obtained and is aligned with the distribution with the consistency constraint of pseudo labels. The cross-view distribution alignment constraint is used to guide the clustering process to obtain a more reliable pseudo label. The comprehensive comparative experiments are done in two public datasets, i.e. Market-1501 and DukeMTMC-reID. The comparative results show that the proposed method outperforms several state-of-the-art approaches with mAP reaching 52.6% and rank1 71.1%. In order to prove the effectiveness of the proposed CV-DA, the proposed constraint is added into two advanced re-ID methods. The experimental results demonstrate that the mAP and rank increase by ?0.5-2% after using the cross-view distribution alignment constraint comparing with that of the associated original methods without using CV-DA.
引用:
复制并粘贴一种已设定好的引用格式,或利用其中一个链接导入到文献管理软件中。
GB/T 7714 | Jia, Xibin , Wang, Xing , Mi, Qing . An unsupervised person re-identification approach based on cross-view distribution alignment [J]. | IET IMAGE PROCESSING , 2021 , 15 (11) : 2693-2704 . |
MLA | Jia, Xibin et al. "An unsupervised person re-identification approach based on cross-view distribution alignment" . | IET IMAGE PROCESSING 15 . 11 (2021) : 2693-2704 . |
APA | Jia, Xibin , Wang, Xing , Mi, Qing . An unsupervised person re-identification approach based on cross-view distribution alignment . | IET IMAGE PROCESSING , 2021 , 15 (11) , 2693-2704 . |
导入链接 | NoteExpress RIS BibTex |
引用:
复制并粘贴一种已设定好的引用格式,或利用其中一个链接导入到文献管理软件中。
GB/T 7714 | Kim, Soo Kyun , Choi, Min-Hyung , Chun, Junchul et al. Real-time 2D/ 3D image processing with deep learning [J]. | MULTIMEDIA TOOLS AND APPLICATIONS , 2021 . |
MLA | Kim, Soo Kyun et al. "Real-time 2D/ 3D image processing with deep learning" . | MULTIMEDIA TOOLS AND APPLICATIONS (2021) . |
APA | Kim, Soo Kyun , Choi, Min-Hyung , Chun, Junchul , Jia, Xibin . Real-time 2D/ 3D image processing with deep learning . | MULTIMEDIA TOOLS AND APPLICATIONS , 2021 . |
导入链接 | NoteExpress RIS BibTex |
摘要 :
本发明公开了基于知识图谱的问答系统的关系检测方法,属于自然语言智能问答技术领域;本发明考虑到问句意图对于答案的选择具有影响,提出加入问句意图辅助检测关系的方法,并在匹配知识图谱信息与自然语言问句时,提出了一种双向注意力机制的Bi‑GRU编码算法,考虑知识图谱中关系信息对问句中每个单词的关注程度差异的同时,考虑计算问句对关系信息的注意力,利用问句的不同表示与关系不同信息的注意力加权来计算问句与知识图谱关系匹配的相似度。改进后的双向注意力关系检测模型,有效提升了对知识图谱中不同候选关系与问题相似度的动态自适应加权,充分利用全局语义信息的同时关注重点信息,从而检索出问句关联度更高的答案。
引用:
复制并粘贴一种已设定好的引用格式,或利用其中一个链接导入到文献管理软件中。
GB/T 7714 | 贾熹滨 , 刘洋 . 基于知识图谱的问答系统的关系检测方法 : CN202010193257.9[P]. | 2020-03-18 . |
MLA | 贾熹滨 et al. "基于知识图谱的问答系统的关系检测方法" : CN202010193257.9. | 2020-03-18 . |
APA | 贾熹滨 , 刘洋 . 基于知识图谱的问答系统的关系检测方法 : CN202010193257.9. | 2020-03-18 . |
导入链接 | NoteExpress RIS BibTex |
摘要 :
本发明公开了一种基于多模态影像贡献度融合的肝细胞癌分化评估方法,首先,建立有效高维多模态影像数据的关联表示,即选择一种合适的特征提取方式对多模态MRI影像进行特征提取,同时,利用多模态MRI影像贡献度自适应加权机制,对九个模态的MRI影像进行任务贡献度学习,然后将任务贡献度学习所得的参数结果与多模态融合MRI数据经过特征提取器所得的特征进行特征层融合,最后,在网络顶端添加分类器,使用结合了贡献度的多模态MRI影像特征进行HCC分化程度的分级任务,以实现更为精准的预测。比起传统影像学诊断方法,本发明排除了主观因素的影响并同时考虑到了各个多模态MRI序列的诊断能力和贡献,从而使得到的结果更加准确和鲁棒。
引用:
复制并粘贴一种已设定好的引用格式,或利用其中一个链接导入到文献管理软件中。
GB/T 7714 | 贾熹滨 , 孙政 , 杨正汉 et al. 一种基于多模态影像贡献度融合的肝细胞癌分化评估方法 : CN202010405639.3[P]. | 2020-05-14 . |
MLA | 贾熹滨 et al. "一种基于多模态影像贡献度融合的肝细胞癌分化评估方法" : CN202010405639.3. | 2020-05-14 . |
APA | 贾熹滨 , 孙政 , 杨正汉 , 杨大为 . 一种基于多模态影像贡献度融合的肝细胞癌分化评估方法 : CN202010405639.3. | 2020-05-14 . |
导入链接 | NoteExpress RIS BibTex |
摘要 :
本发明公开了基于生成对抗网络为医疗影像数据集做数据增广的GAN网络架构及方法,包括:获取现有医疗影像的真实数据集;在样本中,取出含病灶的样本与不含病灶的样本,作为一组一起输入,运行一个循环生成式对抗网络,得到与真实数据相似的人工样本;将人工样本加入到真实数据集中,得到混合数据集;将混合数据集作为输入,使用分类器进行分类任务。本发明引入重建一致性损失函数约束条件,实现从源分布转换为目标分布,然后重建源分布;最后在鉴别器中增加了稳定归一化层,有效地模拟了真实数据的分布特征,通过生成对抗网络生成图像,进行数据增强,然后仿真了大量医疗影像图像样本,有效改善了数据样本不足对医疗影像数据分类任务造成的影响。
引用:
复制并粘贴一种已设定好的引用格式,或利用其中一个链接导入到文献管理软件中。
GB/T 7714 | 贾熹滨 , 毕光耀 . 基于生成对抗网络为医疗影像数据集做数据增广的GAN网络架构及方法 : CN202010304146.0[P]. | 2020-04-17 . |
MLA | 贾熹滨 et al. "基于生成对抗网络为医疗影像数据集做数据增广的GAN网络架构及方法" : CN202010304146.0. | 2020-04-17 . |
APA | 贾熹滨 , 毕光耀 . 基于生成对抗网络为医疗影像数据集做数据增广的GAN网络架构及方法 : CN202010304146.0. | 2020-04-17 . |
导入链接 | NoteExpress RIS BibTex |
导出
数据: |
选中 到 |
格式: |