Weifu Li
YOU?
Author Swipe
View article: Clustering-Guided Multi-Layer Contrastive Representation Learning for Citrus Disease Classification
Clustering-Guided Multi-Layer Contrastive Representation Learning for Citrus Disease Classification Open
Citrus, as one of the most economically important fruit crops globally, suffers severe yield depressions due to various diseases. Accurate disease detection and classification serve as critical prerequisites for implementing targeted contr…
View article: Error Analysis Affected by Heavy-Tailed Gradients for Non-Convex Pairwise Stochastic Gradient Descent
Error Analysis Affected by Heavy-Tailed Gradients for Non-Convex Pairwise Stochastic Gradient Descent Open
In recent years, there have been a growing number of works studying the generalization properties of stochastic gradient descent (SGD) from the perspective of algorithmic stability. However, few of them devote to simultaneously studying th…
View article: Financing Mechanisms and Preferences of Technology-Driven Small- and Medium-Sized Enterprises in the Digitalization Context
Financing Mechanisms and Preferences of Technology-Driven Small- and Medium-Sized Enterprises in the Digitalization Context Open
In the context of digitalization, this study investigated the financing mechanisms and preferences of technology-driven small and medium-sized enterprises (TDSMEs) listed on the National Equities Exchange and Quotations (NEEQ) in China. It…
View article: Big data and artificial intelligence‐aided crop breeding: Progress and prospects
Big data and artificial intelligence‐aided crop breeding: Progress and prospects Open
The past decade has witnessed rapid developments in gene discovery, biological big data (BBD), artificial intelligence (AI)‐aided technologies, and molecular breeding. These advancements are expected to accelerate crop breeding under the p…
View article: Identifying vulnerable populations in urban society: a case study in a flood-prone district of Wuhan, China
Identifying vulnerable populations in urban society: a case study in a flood-prone district of Wuhan, China Open
In the context of unprecedented extreme weather and climatic events, the internal structural factors of society play a decisive role in determining the extent to which human beings are affected by disasters and their ability to respond to …
View article: Higher-order random network models
Higher-order random network models Open
Most existing random network models that describe complex systems in nature and society are developed through connections that indicate a binary relationship between two nodes. However, real-world networks are so complicated that we can on…
View article: VISN: virus instance segmentation network for TEM images using deep attention transformer
VISN: virus instance segmentation network for TEM images using deep attention transformer Open
The identification of viruses from negative staining transmission electron microscopy (TEM) images has mainly depended on experienced experts. Recent advances in artificial intelligence have enabled virus recognition using deep learning te…
View article: Sichuan Cuisine Recognition Method based on Residual Neural Network
Sichuan Cuisine Recognition Method based on Residual Neural Network Open
To address issues such as the high number of parameters, significant variations among images of similar dishes, weak geometric invariance, and low recognition rates in Sichuan cuisine recognition methods, a lightweight Sichuan cuisine reco…
View article: Stability-Based Generalization Analysis for Mixtures of Pointwise and Pairwise Learning
Stability-Based Generalization Analysis for Mixtures of Pointwise and Pairwise Learning Open
Recently, some mixture algorithms of pointwise and pairwise learning (PPL) have been formulated by employing the hybrid error metric of “pointwise loss + pairwise loss” and have shown empirical effectiveness on feature selection, ranking a…
View article: On the Stability and Generalization of Triplet Learning
On the Stability and Generalization of Triplet Learning Open
Triplet learning, i.e. learning from triplet data, has attracted much attention in computer vision tasks with an extremely large number of categories, e.g., face recognition and person re-identification. Albeit with rapid progress in desig…
View article: Stepdown SLOPE for Controlled Feature Selection
Stepdown SLOPE for Controlled Feature Selection Open
Sorted L-One Penalized Estimation (SLOPE) has shown the nice theoretical property as well as empirical behavior recently on the false discovery rate (FDR) control of high-dimensional feature selection by adaptively imposing the non-increas…
View article: Using time series to predict the change in the U.S. unemployment rate at covid-19
Using time series to predict the change in the U.S. unemployment rate at covid-19 Open
To some extent, the unemployment rate can measure the economic situation of a country, generally speaking, the economic development is good during the period of low unemployment, and there are relatively few social contradictions and probl…
View article: Comment on nhess-2022-277
Comment on nhess-2022-277 Open
Abstract. In the context of unprecedented extreme weather and climate events, the internal structural factors of society play a decisive role in the extent to which human beings are affected by disasters and their ability to respond to dis…
View article: Comment on nhess-2022-277
Comment on nhess-2022-277 Open
Abstract. In the context of unprecedented extreme weather and climate events, the internal structural factors of society play a decisive role in the extent to which human beings are affected by disasters and their ability to respond to dis…
View article: Comment on nhess-2022-277
Comment on nhess-2022-277 Open
Abstract. In the context of unprecedented extreme weather and climate events, the internal structural factors of society play a decisive role in the extent to which human beings are affected by disasters and their ability to respond to dis…
View article: Variable Selection Using Deep Variational Information Bottleneck with Drop-Out-One Loss
Variable Selection Using Deep Variational Information Bottleneck with Drop-Out-One Loss Open
The information bottleneck (IB) model aims to find the optimal representations of input variables with respect to the response variable. While it has been widely used in the machine-learning community, research from the perspective of the …
View article: Reply on AC1
Reply on AC1 Open
Abstract. In the context of unprecedented extreme weather and climate events, the internal structural factors of society play a decisive role in the extent to which human beings are affected by disasters and their ability to respond to dis…
View article: Stepdown SLOPE for Controlled Feature Selection
Stepdown SLOPE for Controlled Feature Selection Open
Sorted L-One Penalized Estimation (SLOPE) has shown the nice theoretical property as well as empirical behavior recently on the false discovery rate (FDR) control of high-dimensional feature selection by adaptively imposing the non-increas…
View article: On the Stability and Generalization of Triplet Learning
On the Stability and Generalization of Triplet Learning Open
Triplet learning, i.e. learning from triplet data, has attracted much attention in computer vision tasks with an extremely large number of categories, e.g., face recognition and person re-identification. Albeit with rapid progress in desig…
View article: Stability-based Generalization Analysis for Mixtures of Pointwise and Pairwise Learning
Stability-based Generalization Analysis for Mixtures of Pointwise and Pairwise Learning Open
Recently, some mixture algorithms of pointwise and pairwise learning (PPL) have been formulated by employing the hybrid error metric of "pointwise loss + pairwise loss" and have shown empirical effectiveness on feature selection, ranking a…
View article: Comment on nhess-2022-277
Comment on nhess-2022-277 Open
Abstract. In the context of unprecedented extreme weather and climate events, the internal structural factors of society play a decisive role in the extent to which human beings are affected by disasters and their ability to respond to dis…
View article: Identifying Vulnerable Population in the Urban Society: a Case Study of Wuhan, China
Identifying Vulnerable Population in the Urban Society: a Case Study of Wuhan, China Open
In the context of unprecedented extreme weather and climate events, the internal structural factors of society play a decisive role in the extent to which human beings are affected by disasters and their ability to respond to disasters. In…
View article: Predicting and Visualizing Citrus Color Transformation Using a Deep Mask-Guided Generative Network
Predicting and Visualizing Citrus Color Transformation Using a Deep Mask-Guided Generative Network Open
Citrus rind color is a good indicator of fruit development, and methods to monitor and predict color transformation therefore help the decisions of crop management practices and harvest schedules. This work presents the complete workflow t…
View article: DeepBSA: A deep-learning algorithm improves bulked segregant analysis for dissecting complex traits
DeepBSA: A deep-learning algorithm improves bulked segregant analysis for dissecting complex traits Open
Bulked segregant analysis (BSA) is a rapid, cost-effective method for mapping mutations and quantitative trait loci (QTLs) in animals and plants based on high-throughput sequencing. However, the algorithms currently used for BSA have not b…
View article: Gradient Learning under Tilted Empirical Risk Minimization
Gradient Learning under Tilted Empirical Risk Minimization Open
Gradient Learning (GL), aiming to estimate the gradient of target function, has attracted much attention in variable selection problems due to its mild structure requirements and wide applicability. Despite rapid progress, the majority of …