Explanipedia

V‐UNet: Medical Image Segmentation Based on Variational Attention Mechanism Open

Yang Zhang, Qiang Yang, Li Tian, Fanghong Zhang, Yu Ren , et al. · 2025

Accurate medical image segmentation plays a crucial role in improving the precision of computer‐aided diagnosis. However, complex boundary shapes, low contrast and blurred anatomical structures make fine‐grained segmentation a challenging …

Aligning to the teacher: multilevel feature-aligned knowledge distillation Open

Yang Zhang, Pan He, Chuanyun Xu, Jodie Pang, Xiao Wang , et al. · 2025

Knowledge distillation is a technique for transferring knowledge from a teacher’s (large) model to a student’s (small) model. Usually, the features of the teacher model contain richer information, while the features of the student model ca…

A Rapid Sand Gradation Detection Method Based on Dual-Camera Fusion Open

Shihao Zhang, Yang Zhang, Song Sun, Xinghai Yuan, Haoxuan Sun , et al. · 2025

Precise grading of manufactured sand is vital to concrete performance, yet standard sieve tests, though accurate, are too slow for online quality control. Thus, we devised an image-based inspection method combining a dual-camera module wit…

Two-stage optimization based on heterogeneous branch fusion for knowledge distillation Open

Gang Li, Pengfei Lv, Yang Zhang, Chuanyun Xu, Zihan Ruan , et al. · 2025

Knowledge distillation transfers knowledge from the teacher model to the student model, effectively improving the performance of the student model. However, relying solely on the fixed knowledge of the teacher model for guidance lacks the …

DualBranch‐FusionNet: A Hybrid CNN‐Transformer Architecture for Cervical Cell Image Classification Open

Chuanyun Xu, Simon Huang, Yang Zhang, Die Hu, Yisha Sun , et al. · 2025

Cervical cancer screening relies on accurate cell classification. Approaches based on Convolutional Neural Networks (CNNs) have proven effective in addressing the task. However, these approaches suffer from two main challenges. First, they…

Stain Normalization of Histopathological Images Based on Deep Learning: A Review Open

Chuanyun Xu, Yisha Sun, Yang Zhang, Tianqi Liu, Xiao Wang , et al. · 2025

Histopathological images stained with hematoxylin and eosin (H&E) are crucial for cancer diagnosis and prognosis. However, color variations caused by differences in tissue preparation and scanning devices can lead to data distribution disc…

Detection of cervical cell based on multi-scale spatial information Open

Gang Li, Xinyu Fan, Chuanyun Xu, Pengfei Lv, Ru Wang , et al. · 2025

Implicit Feature Contrastive Learning for Few-Shot Object Detection Open

Gang Li, Zheng Zhou, Yang Zhang, Chuanyun Xu, Zihan Ruan , et al. · 2025

Multi-Scale Feature Fusion Network for Accurate Detection of Cervical Abnormal Cells Open

Chuanyun Xu, Die Hu, Yang Zhang, Simon Huang, Yisha Sun , et al. · 2025

LR-Net: Lossless Feature Fusion and Revised SIoU for Small Object Detection Open

Gang Li, Ru Wang, Yang Zhang, Chuanyun Xu, Xinyu Fan , et al. · 2025

Short-Term Water Supply Forecasting for Water Treatment Plant Using Temporal Multi-Scale Features Open

Yang Zhang, Junjie Li, Song Sun, Gang Li, Qiang Yang , et al. · 2024

Forecasting the water supply of a water treatment plant is an important management and decision-making task in the water treatment system. Currently, most studies in this field do not consider the problems brought about by the time scale w…

Analysis of type 2 diabetes mellitus‐related genes by constructing the pathway‐based weighted network Open

Xueyan Zhang, Chuanyun Xu, Ke‐Fei Cao, Hong Luo, Xu‐Sheng Zhang · 2024

Complex network is an effective approach to studying complex diseases, and provides another perspective for understanding their pathological mechanisms by illustrating the interactions between various factors of diseases. Type 2 diabetes m…

Sand gradation detection method based on local sampling Open

Yang Zhang, Dazhi Hou, Chuanyun Xu, Heng Wang, Liping Peng , et al. · 2024

Detection of Cervical Lesion Cell/Clumps Based on Adaptive Feature Extraction Open

Gang Li, Xingguang Li, Yuting Wang, Shu Gong, Yanting Yang , et al. · 2024

Automated detection of cervical lesion cell/clumps in cervical cytological images is essential for computer-aided diagnosis. In this task, the shape and size of the lesion cell/clumps appeared to vary considerably, reducing the detection p…

Local Contrast Learning for One-Shot Learning Open

Yang Zhang, Xinghai Yuan, Ling Luo, Yulu Yang, Shihao Zhang , et al. · 2024

Learning a deep model from small data is an opening and challenging problem. In high-dimensional spaces, few samples only occupy an extremely small portion of the space, often exhibiting sparsity issues. Classifying in this globally sparse…

Multistage feature fusion knowledge distillation Open

Gang Li, Kun Wang, Pengfei Lv, Pan He, Zheng Zhou , et al. · 2024

Generally, the recognition performance of lightweight models is often lower than that of large models. Knowledge distillation, by teaching a student model using a teacher model, can further enhance the recognition accuracy of lightweight m…

Dual-Branch Multi-Scale Relation Networks with Tutorial Learning for Few-Shot Learning Open

Chuanyun Xu, Hang Wang, Yang Zhang, Zheng Zhou, Gang Li · 2024

Few-shot learning refers to training a model with a few labeled data to effectively recognize unseen categories. Recently, numerous approaches have been suggested to improve the extraction of abundant feature information at hierarchical la…

Development of a generative model for a mobile robot operated in everyday environments and its evaluation by pilot experiment with data collection Open

Chuanyun Xu, Yuya Okadome, Hiroshi Ishiguro, Yutaka Nakamura · 2024

Anchor-Free Smoke and Flame Recognition Algorithm with Multi-Loss Open

Gang Li, Peng Chen, Chuanyun Xu, Chengjie Sun, Yingli Ma · 2023

Fire perception based on machine vision is essential for improving social safety. Object recognition based on deep learning has become the mainstream smoke and flame recognition method. However, the existing anchor-based smoke and flame re…

Combining convolutional neural networks and self-attention for fundus diseases identification Open

Keya Wang, Chuanyun Xu, Gang Li, Yang Zhang, Yu Zheng , et al. · 2023

Early detection of lesions is of great significance for treating fundus diseases. Fundus photography is an effective and convenient screening technique by which common fundus diseases can be detected. In this study, we use color fundus ima…

Cervical Cell Image Classification-Based Knowledge Distillation Open

Wenjian Gao, Chuanyun Xu, Gang Li, Yang Zhang, Nanlan Bai , et al. · 2022

Current deep-learning-based cervical cell classification methods suffer from parameter redundancy and poor model generalization performance, which creates challenges for the intelligent classification of cervical cytology smear images. In …

Cervical Cell/Clumps Detection in Cytology Images Using Transfer Learning Open

Chuanyun Xu, Mengwei Li, Gang Li, Yang Zhang, Chengjie Sun , et al. · 2022

Cervical cancer is one of the most common and deadliest cancers among women and poses a serious health risk. Automated screening and diagnosis of cervical cancer will help improve the accuracy of cervical cell screening. In recent years, t…

Multigranularity Syntax Guidance with Graph Structure for Machine Reading Comprehension Open

Chuanyun Xu, Zixu Liu, Gang Li, Changpeng Zhu, Yang Zhang · 2022

In recent years, pre-trained language models, represented by the bidirectional encoder representations from transformers (BERT) model, have achieved remarkable success in machine reading comprehension (MRC). However, limited by the structu…

Multiple-Stage Knowledge Distillation Open

Chuanyun Xu, Nanlan Bai, Wenjian Gao, Tian Li, Mengwei Li , et al. · 2022

Knowledge distillation (KD) is a method in which a teacher network guides the learning of a student network, thereby resulting in an improvement in the performance of the student network. Recent research in this area has concentrated on de…

MBSaNet : A combination of convolutional neural networks and self-attention for the identification of fundus diseases Open

Keya Wang, Chuanyun Xu, Gang Li, Yu Zheng, Chengjie Sun , et al. · 2022

Early detection of lesions is of great significance for treating fundus diseases. Fundus photography is an effective and convenient screening technique by which common fundus diseases can be detected. In this study, we use color fundus ima…

Cervical Cell Segmentation Method Based on Global Dependency and Local Attention Open

Gang Li, Chengjie Sun, Chuanyun Xu, Yu Zheng, Keya Wang · 2022

The refined segmentation of nuclei and the cytoplasm is the most challenging task in the automation of cervical cell screening. The U-Shape network structure has demonstrated great superiority in the field of biomedical imaging. However, t…

Teacher-student collaborative knowledge distillation for image classification Open

Chuanyun Xu, Wenjian Gao, Tian Li, Nanlan Bai, Gang Li , et al. · 2022

A single model usually cannot learn all the appropriate features with limited data, thus leading to poor performance when test data are used. To improve model performance, we propose a teacher-student collaborative knowledge distillation (…

A method for detecting objects in dense scenes Open

Chuanyun Xu, Yu Zheng, Yang Zhang, Gang Li, Ying Wang · 2022

Recent object detectors have achieved excellent performance in accuracy and speed. Even with such impressive results, the most advanced detectors are challenging in dense scenes. In this article, we analyze and find the reasons for the dec…

Cascaded Feature-Mask Fusion for Foreground Segmentation Open

Chuanyun Xu, Huan Liu, Tenghui Li, Yang Zhang, Li Tian , et al. · 2022

Foreground segmentation aims at extracting moving objects from the background in a robust manner under various challenging scenarios. The deep learning-based methods have achieved remarkable improvement in this field. These methods produce…

Local Contrast Learning Open

Chuanyun Xu, Yang Zhang, Xin Feng, Yongxing Ge, Yihao Zhang , et al. · 2018

Learning a deep model from small data is yet an opening and challenging problem. We focus on one-shot classification by deep learning approach based on a small quantity of training samples. We proposed a novel deep learning approach named …

Chuanyun Xu YOU? Author Swipe