检索结果-内蒙古大学图书馆

SAT-Net: Structure-Aware Transformer-Based Attention Fusion Network for Low-Quality Retinal Fundus images Enhancement

引用

IEEE Transactions on Multimedia 2025年

作者： Wen, Yang Luo, Bin Shi, Wuzhen Ji, Jianhua Cao, Wenming Yang, Xiaokang Sheng, Bin Shenzhen University Guangdong Provincial Key Laboratory of Intelligent Information Processing College of Electronics and Information Engineering Shenzhen China Shanghai Jiao Tong University AI Institute Shanghai China Shanghai Jiao Tong University Department of Computer Science and Engineering Shanghai China

In ophthalmology diagnosis, high-fidelity fundus images are essential for disease diagnosis and intervention. However, many real-world clinical conditions may degrade the quality of the acquired images and thus affect clinical diagnostic accuracy. Traditional convolutional neural network-based retinal fundus image enhancement methods cannot always capture long-range dependencies, which reduces the overall visual quality of images, especially for real retinal fundus images. Furthermore, existing enhancement methods often fail to fully utilize low-resolution structural detail information, which potentially leads to inaccurate pivotal fundus vessel topology or capillary details. In this paper, we propose a novel Structure-Aware Transformer-based attention fusion Network (SAT-Net) for low-quality retinal fundus image enhancement. First, we introduce a Transformer-based attention fusion module which incorporates window-based self-attention and channel self-attention to capture global spatial dependencies and emphasize important feature channels simultaneously. This fusion significantly improves the overall perceptual quality of the image by enhancing both the local details and the uniformity of the non-vessel background regions. Second, we introduce a cross-quality knowledge distillation technique, which bridges the quality gap between high-quality and low-quality fundus images. By designing a high-performing teacher network to guide a lightweight student network, the student network enables to capture detailed features from low-quality fundus images, further preserving critical diagnostic information and fine topology structures. Moreover, we design a structure-aware multi-scale loss function by using a trainable subnetwork to obtain the edge structure from different scales to better constrain pivotal fundus vessel structure and capillary details. Comprehensive quantitative and qualitative experiments on both synthetic and real fundus image datasets robustly validate th

关键词： Students

来源：评论

学校读者我要写书评

暂无评论

Report-Guided Cross-Modal Representation Learning for Predicting EGFR Mutations by Whole Slide image

Report-Guided Cross-Modal Representation Learning for Predic...

引用

IEEE International Conference on Bioinformatics and Biomedicine (BIBM)

作者： Qi Qiao Jun Shi Zhiguo Jiang Wei Wang Haibo Wu Yushan Zheng School of Computer Science and Information Engineering Hefei University of Technology Hefei China School of Software Hefei University of Technology Hefei China Image Processing Center School of Astronautics Beihang University Beijing China Department of Pathology the First Affiliated Hospital of USTC Division of Life Sciences and Medicine University of Science and Technology of China Hefei China Intelligent Pathology Institute Division of Life Sciences and Medicine University of Science and Technology of China Hefei China School of Engineering Medicine Beijing Advanced Innovation Center for Biomedical Engineering Beihang University Beijing China

ISBN: (数字)9798350386226

ISBN: (纸本)9798350386233

Traditional PCR/NGS-based multigene panel testing is time-consuming and costly. Predicting EGFR mutations directly from H&E stained whole slide images (WSIs) can alleviate these limitations. Furthermore, histopathological reports contain valuable textual information that correlates with tissue areas in WSIs. However, recent research mainly analyses EGFR mutation status only from a single modality, ignoring rich information contained in reports. In this paper, we propose a report-guided cross-modal representation learning method for predicting EGFR mutations by WSIs. Specifically, we reconstruct report-level embeddings through exploring intrinsic relationships between diagnostic words in histopathological reports and tissue areas in WSIs. Finally, reconstructed histopathological report embedding and aggregated WSI embedding are fused for final prediction. More importantly, molecular testing report is also introduced as prior supervision information at the training stage to guarantee semantic consistency of fused feature and molecular report embedding. We evaluate our method on the TCGA-EGFR public benchmark dataset and an in-house clinical dataset (USTC-EGFR). Experimental results demonstrate that our method outperforms existing approaches in EGFR mutation prediction, highlighting the benefits of cross-modal learning in enhancing feature representational ability. The code is available at https://***/HFUT-miaLab/RCRL.

关键词： Representation learning Training Codes Supervised learning Semantics Medical treatment Benchmark testing Bioinformatics image reconstruction Biomedical imaging

来源：评论

学校读者我要写书评

暂无评论

Spatial-Frequency Discriminability for Revealing Adversarial Perturbations

arXiv

引用

arXiv 2023年

作者： Wang, Chao Qi, Shuren Huang, Zhiqiu Zhang, Yushu Lan, Rushi Cao, Xiaochun Fan, Feng-Lei The College of Computer Science and Technology Nanjing University of Aeronautics and Astronautics Nanjing211106 China The Department of Mathematics The Chinese University of Hong Kong Hong Kong The Guangxi Key Laboratory of Image and Graphic Intelligent Processing Guilin University of Electronic Technology Guilin541004 China The School of Cyber Science and Technology Shenzhen Campus of Sun Yat-sen University Shenzhen518107 China

The vulnerability of deep neural networks to adversarial perturbations has been widely perceived in the computer vision community. From a security perspective, it poses a critical risk for modern vision systems, e.g., the popular Deep Learning as a Service (DLaaS) frameworks. For protecting deep models while not modifying them, current algorithms typically detect adversarial patterns through discriminative decomposition for natural and adversarial data. However, these decompositions are either biased towards frequency resolution or spatial resolution, thus failing to capture adversarial patterns comprehensively. Also, when the detector relies on few fixed features, it is practical for an adversary to fool the model while evading the detector (i.e., defense-aware attack). Motivated by such facts, we propose a discriminative detector relying on a spatial-frequency Krawtchouk decomposition. It expands the above works from two aspects: 1) the introduced Krawtchouk basis provides better spatial-frequency discriminability, capturing the differences between natural and adversarial data comprehensively in both spatial and frequency distributions, w.r.t. the common trigonometric or wavelet basis;2) the extensive features formed by the Krawtchouk decomposition allows for adaptive feature selection and secrecy mechanism, significantly increasing the difficulty of the defense-aware attack, w.r.t. the detector with few fixed features. Theoretical and numerical analyses demonstrate the uniqueness and usefulness of our detector, exhibiting competitive scores on several deep models and image sets against a variety of adversarial attacks. Copyright © 2023, The Authors. All rights reserved.

关键词： Generative adversarial networks

来源：评论

学校读者我要写书评

暂无评论

40 Gb/s High-speed mode-division multiplexing transmission employing NRZ modulation format

引用

Journal of Optical Communications 2023年第s1期44卷 S1157-S1165页

作者： Sabitu, Rabiu Imam Khan, Nafizah Goriman Malekmohammadi, Amin Affiliated to the George Green Institute for Electromagnetics Research Nottingham United Kingdom Photonics Communication Systems and Signal Processing Research Group Kano University of Science and Technology Wudil KanoPMB 3244 Nigeria Semenyih Malaysia Department of Electrical and Computer Engineering California State University BakersfieldCA93311 United States Photonics Communication Systems and Signal Processing Research Group Kano University of Science and Technology Wudil KanoPMB 3244 Nigeria

This report examines the performance of a high-speed MDM transmission system supporting four nondegenerate spatial modes at 10 Gb/s. The analysis adopts the NRZ modulation format to evaluate the system performance in terms of a minimum power required (PN) and the nonlinear threshold power (PTH) at a BER of 10−9. The receiver sensitivity, optical signal-to-noise ratio, and the maximum transmission distance were investigated using the direct detection by employing a multimode erbium-doped amplifier (MM-EDFA). It was found that by properly optimizing the MM-EDFA, the system performance can significantly be improved. © 2023 Walter de Gruyter GmbH. All rights reserved.

关键词： Erbium doped fiber amplifiers

来源：评论

学校读者我要写书评

暂无评论

A Survey on Network Management for xANET: Evolution, Challenges, Future Directions

引用

IEEE Communications Surveys and Tutorials 2025年

作者： Li, Tong Yang, Chungang Wang, Yao Cai, Lin Anpalagan, Alagan Han, Zhu Xidian University State Key Laboratory of Integrated Services Networks Xi'an710071 China National Key Laboratory of Multi-domain Data Collaborative Processing and Control Xi'an710068 China Hangzhou Institute of Technology of Xidian University Hangzhou311231 China University of Victoria Department of Electrical and Computer Engineering VictoriaBCV8P 5C2 Canada Ryerson University Department of Electrical and Computer Engineering TorontoONM5B 2K3 Canada University of Houston Department of Electrical and Computer Engineering HoustonTX77004 United States Kyung Hee University Department of Computer Science and Engineering Seoul446701 Korea Republic of

The x ad hoc network (xANET) termed as a family of ad hoc networks, including mobile ad hoc network (MANET), vehicular ad hoc network (VANET), flying ad hoc network (FANET) and satellite ad hoc network (SANET), has found a wide range of applications in providing ubiquitous wireless services. Despite its broad utility, the dynamic nature and lack of a centralized controller pose significant challenges to effective and flexible network management for xANET. Conventional network management protocols face challenges such as scalability, security vulnerabilities, configuration complexity, robustness, and performance resilience. Recent efforts have presented different approaches, focusing on policy-based network management (PBNM) and intent-driven network management (IDNM). However, there is no comprehensive survey to clarify their concepts and classifications. This paper presents a survey of the network management evolution for xANET, covering configuration-based, policy-based and the latest intent-driven approaches. We first introduce the characteristics and applications of xANET. Meanwhile, we investigate the network management concepts and challenges. Moreover, we survey the evolution of management protocols for xANET, including simple network management protocol (SNMP), PBNM, and IDNM. Then, we follow the detailed network management of xANET from configuration-based to policy-based and intent-driven approaches. Through comparative analysis, it is found that IDNM employs a more intelligent management protocol, demonstrating higher efficiency and flexibility in handling complex tasks and dynamic network management. This makes it better suited to addressing the challenges of xANET management. Finally, we summarize the remaining challenges and possible future research directions. © 2025 IEEE.

关键词： Vehicular ad hoc networks

来源：评论

学校读者我要写书评

暂无评论

Multi-material additive manufacturing of thermocouples by laser-based powder bed fusion

引用

Procedia CIRP 2022年 112卷 346-351页

作者： Christopher Singer Matthias Schmitt Georg Schlick Johannes Schilp Fraunhofer IGCV (Research Institute for Casting Composite and Processing Technology) Am Technologiezentrum 10 86159 Augsburg University of Augsburg Chair of Digital Manufacturing Department of Applied Computer Science Universitätsstraße 2 86159 Augsburg Germany

Multi-material additive manufacturing by laser-based powder bed fusion (PBF-LB) enables arbitrary material composition in components and thus enables the manufacturing of so-called smart parts. By combining different materials sensoric structures can be implemented into components. This paper investigates the possibilities to manufacture thermocouples (TC) consisting of two nickel-based alloys by the means of PBF-LB. These alloys are qualified to achieve sufficient relative densities for the thermocouples. Furthermore, the electrical conductivity of the parts is measured and compared to literature values. Finally, additively manufactured thermocouples are tested in comparison to conventional thermocouples in the temperature range from 50 to 350°C.

关键词： metal additive manufacturing sensor printing thermocouples smart parts laser-based powder bed fusion laser beam melting multi-material

来源：评论

学校读者我要写书评

暂无评论

Development of an Automated Process Chain for Hybrid Additive Manufacturing using Laser Powder Bed Fusion

引用

Procedia CIRP 2022年 112卷 358-363页

作者： Lukas Langer Matthias Schmitt Georg Schlick Johannes Schilp Fraunhofer IGCV (Research Institute for Casting Composite and Processing Technology) Am Technologiezentrum 10 86159 Augsburg University of Augsburg Chair of Digital Manufacturing Department of Applied Computer Science Universitätsstraße 2 86159 Augsburg Germany

Additive Manufacturing (AM) offers great potential for producing complex parts. However, the economical fabrication depends among others on the part height. Hence, the combination of a conventionally manufactured base body and AM offers potential to reduce part costs. This combination is called Hybrid Additive Manufacturing (HAM) and requires additional clamping mechanisms and a positioning system in the laser powder bed fusion process. Concepts for both requirements will be investigated within this paper. In order to increase flexibility and automation a concept for an automated process chain will be developed. The requirements and properties of the process chain will be discussed.

关键词： Hybrid Additive Manufacturing Automation Subtractive Manufacturing Clamping Positioning Metrology

来源：评论

学校读者我要写书评

暂无评论

Toward a Unified Framework for Unsupervised Complex Tabular Reasoning

Toward a Unified Framework for Unsupervised Complex Tabular ...

引用

International Conference on Data Engineering

作者： Zhenyu Li Xiuxing Li Zhichao Duan Bowen Dong Ning Liu Jianyong Wang Department of Computer Science and Technology Tsinghua University Beijing China Key Laboratory of Intelligent Information Processing Institute of Computing Technology Chinese Academy of Sciences (ICT/CAS) University of Chinese Academy of Sciences School of Software Shandong University Jinan China

Structured tabular data exist across nearly all fields. Reasoning task over these data aims to answer questions or determine the truthiness of hypothesis sentences by understanding the semantic meaning of a table. While previous works have devoted significant efforts to the tabular reasoning task, they always assume there are sufficient labeled data. However, constructing reasoning samples over tables (and related text) is labor-intensive, especially when the reasoning process is complex. When labeled data is insufficient, the performance of models will suffer an unendurable decline. In this paper, we propose a unified framework for unsupervised complex tabular reasoning (UCTR), which generates sufficient and diverse synthetic data with complex logic for tabular reasoning tasks, assuming no human-annotated data at all. Specifically, we first utilize a random sampling strategy to collect diverse programs of different types and execute them on tables based on a "Program-Executor" module. To bridge the gap between the programs and natural language sentences, we design a powerful "NL-Generator" module to generate natural language sentences with complex logic from these programs. Since a table often occurs with its surrounding texts, we further propose novel "Table-to-Text" and "Text-to-Table" operators to handle joint table-text reasoning scenarios. This way, we can adequately exploit the unlabeled table resources to obtain a well-performed reasoning model under an unsupervised setting. Our experiments cover different tasks (question answering and fact verification) and different domains (general and specific), showing that our unsupervised methods can achieve at most 93% performance compared to supervised models. The impressive performance demonstrates that UCTR can significantly reduce the dependence on manual annotation. Moreover, we also find that it can substantially boost the supervised performance in low-resourced domains as a data augmentation technique.

关键词：

来源：评论

学校读者我要写书评

暂无评论

A Multi-Level Thresholding image Segmentation Based on an Improved Artificial Bee Colony Algorithm 2nd

A Multi-Level Thresholding Image Segmentation Based on an Im...

引用

2nd EAI International Conference on Robotic Sensor Networks, ROSENET 2018

作者： Xia, Xingyu Gao, Hao Hu, Haidong Lan, Rushi Pun, Chi-Man The Institute of Advanced Technology Nanjing University of Posts and Telecommunications Nanjing China Department of Computer and Information Science University of Macau China Beijing Institute of Control Engineering Beijing China Key Laboratory of Intelligent Processing of Computer Image and Graphics Guilin University of Electronic Technology Guilin China

ISBN: (纸本)9783030177621

As a popular evolutionary algorithm, artificial bee colony (ABC) algorithm has been successfully applied into the threshold-based image segmentation problem. Based on our analysis, we find that the Otsu segmentation function is separable which means each variable is independent. Due to its one-dimensional search strategy and relative power global but poorer local search abilities, ABC could find an acceptable but not precise segmentation results. For making more precise search and further enhancing the achievements on image segmentation, we propose an Otsu segmentation method based on a new ABC algorithm with an improved scout bee strategy. Different from the traditional scout bee strategy, we use a local search strategy when a bee stagnates for a defined value. The experimental results on Berkeley segmentation database demonstrate the effectiveness of our algorithm. © 2020, Springer science and Business Media Deutschland GmbH. All rights reserved.

关键词： image segmentation

来源：评论

学校读者我要写书评

暂无评论

Terahertz compressive imaging: understanding and improvement by a better strategy for data selection

Terahertz compressive imaging: understanding and improvement...

引用

作者： Xing, Chungui Qi, Feng Liu, Zhaoyang Wang, Yelong Guo, Shuxu State Key Laboratory on Integrated Optoelectronics College of Electronic Science and Engineering Jilin University Changchun China Shenyang Institute of Automation Chinese Academy of Sciences Shenyang China Key Laboratory of Opto-Electronic Information Processing Chinese Academy of Sciences Shenyang China Key Lab of Image Understanding and Computer Vision Shenyang China

Compressive sensing (CS) is a novel sampling modality, which indicates the signals can be sampled at a rate much below the Nyquist sampling rate. CS has increasing interest recently due to high demand of rapid, efficient, and in-expensive signal processing applications in the μmWave and mmWave frequencies, such as communication and imaging. There have been a lot of theoretical studies on this topic, but there is a lack of systematic experimental analysis of the implementation method itself. In this paper, we have investigated the influencing factors of terahertz compressive sensing based on experimental results, including illumination and the size of the pixel. Besides, to differentiate from current approaches, which generally make full use of the data, we propose to sort the data first and select a part of them based on amplitude, which might deliver a better image by prompting the mathematical calculations compulsively. We believe that such considerations given above would help to make a better system design and improve the performance of compressive imaging, and these results will also be helpful in the application of terahertz communication. © 2021 John Wiley & Sons, Ltd

关键词： Compressed sensing

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：