In recent years, knowledge graph embedding becomes a pretty hot research topic of artificial intelligence and plays increasingly vital roles in various downstream applications, such as recommendation and question answ...
详细信息
Simultaneous localization and mapping (SLAM) technology has always been the research focus of robot navigation in unknown environment. Aiming at the problem of cumulative errors of robot pose in the localization proce...
详细信息
Reduced biquaternions (RBs), as an extension of complex numbers, have demonstrated exceptional capabilities in digital signal and imageprocessing. They not only excel particularly in encoding color information but al...
详细信息
Deep learning has been extensively applied in the field of remote sensing for tasks such as change detection (CD). However, since CD is a pixel-level task, the high cost of data annotation and often limited availabili...
Deep learning has been extensively applied in the field of remote sensing for tasks such as change detection (CD). However, since CD is a pixel-level task, the high cost of data annotation and often limited availability of labelled data significantly restrict the performance of existing deep learning-based CD methods. To mitigate this problem, a novel Language-Guided Change Detection (LGCD) framework is introduced. Within this LGCD network, text information is leveraged to precisely locate changed areas, addressing the shortcomings associated with insufficient labelled imagedata. Also, augmentation semi-supervised learning techniques are employed to generate high-quality pseudo-labels, further reducing the reliance on labelled samples. Additionally, the utilisation of Fusion UNet (FUNet) and Transformer capitalises on their sensitivity to local and global features respectively, offering a comprehensive examination of change features in high-resolution bi-temporal remote sensing imagery. For evaluation purposes, three publicly available CD datasets are exploited. Experimental results demonstrate that the proposed LGCD framework achieves exceptional detection performance in both fully supervised and semi-supervised settings, despite the constraints of limited labelled data.
作者:
Jinyuan FangQiang ZhangZaiqiao MengShangsong LiangSchool of Computer Science and Engineering
Sun Yat-sen University China and Guangdong Key Laboratory of Big Data Analysis and Processing Guangzhou China Hangzhou Innovation Center
Zhejiang University China and College of Computer Science and Technology Zhejiang University China and AZFT Knowledge Engine Lab China School of Computing Science
University of Glasgow United Kingdom and Mohamed bin Zayed University of Artificial Intelligence United Arab Emirates School of Computer Science and Engineering
Sun Yat-sen University China and Guangdong Key Laboratory of Big Data Analysis and Processing Guangzhou China and Mohamed bin Zayed University of Artificial Intelligence United Arab Emirates
Gaussian Processes (GPs) define distributions over functions and their generalization capabilities depend heavily on the choice of kernels. In this paper, we propose a novel structure-aware random Fourier (SRF) kernel...
ISBN:
(纸本)9781713845393
Gaussian Processes (GPs) define distributions over functions and their generalization capabilities depend heavily on the choice of kernels. In this paper, we propose a novel structure-aware random Fourier (SRF) kernel for GPs that brings several benefits when modeling graph-structured data. First, SRF kernel is defined with a spectral distribution based on the Fourier duality given by the Bochner's theorem, transforming the kernel learning problem to a distribution inference problem. Second, SRF kernel admits a random Fourier feature formulation that makes the kernel scalable for optimization. Third, SRF kernel enables to leverage geometric structures by taking subgraphs as inputs. To effectively optimize GPs with SRF kernel, we develop a variational EM algorithm, which alternates between an inference procedure (E-step) and a learning procedure (M-step). Experimental results on five real-world datasets show that our model can achieve state-of-the-art performance in two typical graph learning tasks, i.e., object classification and link prediction.
Classifying diseases in electronic medical records into corresponding ICD codes requires not only a large amount of medical knowledge but also a large number of coders, which is time-consuming and labor-consuming. The...
详细信息
ISBN:
(纸本)9781665429825
Classifying diseases in electronic medical records into corresponding ICD codes requires not only a large amount of medical knowledge but also a large number of coders, which is time-consuming and labor-consuming. Therefore, automatic coding is of great significance. This paper aims to build a deep learning model for automatic ICD-10 coding from a batch of Chinese electronic medical records. The data enhancement, convolutional neural network, attention mechanism, and the gating residual network proposed by the author were used to code ICD code corresponding to the distribution of medical record information by supervised learning. The benchmark model and ablation model were tested on a data set of Chinese electronic medical records. The effectiveness of the proposed modules, such as feature aggregation, multi-head attention mechanism, dilated convolution, and gating residuals, was verified. In the automatic ICD coding task for 104 diseases, the accuracy of the proposed method is 91.71%, and the F1-Score is 92.11%. 1
The multivariate time series forecasting has attracted more and more attention because of its vital role in different fields in the real world, such as finance, traffic, and weather. In recent years, many research eff...
详细信息
Adaptive fuzzy control strategies are established to achieve global prescribed performance with prescribed-time convergence for strict-feedback systems with mismatched uncertainties and unknown nonlinearities. Firstly...
详细信息
Network embedding has recently emerged as a promising technique to embed nodes of a network into low-dimensional vectors. While fairly successful, most existing works focus on the embedding techniques for static netwo...
详细信息
Multitemporal hyperspectral unmixing can capture dynamical evolution of materials. Despite its capability, current methods emphasize variability of endmembers while neglecting dynamics of abundances, which motivates o...
详细信息
暂无评论