检索结果-内蒙古大学图书馆

Learning Accurate Low-bit Quantization towards Efficient Computational Imaging

INTERNATIONAL JOURNAL OF COMPUTER VISION 2025年第4期133卷 1611-1643页

作者： Xu, Sheng Li, Yanjing Liu, Chuanjian Zhang, Baochang Beihang Univ Beijing Peoples R China Huawei Noahs Ark Lab Beijing Peoples R China Hangzhou Res Inst Inst Artificial Intelligence Hangzhou Peoples R China Zhongguancun Lab Beijing Peoples R China NanChang Inst Technol Nanchang Peoples R China

Recent advances of deep neural networks (DNNs) promote low-level vision applications in real-world scenarios, e.g., image enhancement, dehazing. Nevertheless, DNN-based methods encounter challenges in terms of high computational and memory requirements, especially when deployed on real-world devices with limited resources. Quantization is one of effective compression techniques that significantly reduces computational and memory requirements by employing low-bit parameters and bit-wise operations. However, low-bit quantization for computational imaging (Q-Imaging) remains largely unexplored and usually suffer from a significant performance drop compared with the real-valued counterparts. In this work, through empirical analysis, we identify the main factor responsible for such significant performance drop underlies in the large gradient estimation error from non-differentiable weight quantization methods, and the activation information degeneration along with the activation quantization. To address these issues, we introduce a differentiable quantization search (DQS) method to learn the quantized weights and an information boosting module (IBM) for network activation quantization. Our DQS method allows us to treat the discrete weights in a quantized neural network as variables that can be searched. We achieve this end by using a differential approach to accurately search for these weights. In specific, each weight is represented as a probability distribution across a set of discrete values. During training, these probabilities are optimized, and the values with the highest probabilities are chosen to construct the desired quantized network. Moreover, our IBM module can rectify the activation distribution before quantization to maximize the self-information entropy, which retains the maximum information during the quantization process. Extensive experiments across a range of image processing tasks, including enhancement, super-resolution, denoising and dehazing, vali

关键词： Quantization Computational imaging Differentiable quantization search Information entropy

来源：评论

学校读者我要写书评

暂无评论

Explainable deep learning model with the internet of medical devices for early lung abnormality detection

引用

ENGINEERING applications OF artificial INTELLIGENCE 2025年 153卷

作者： Hou, Xin Innab, Nisreen Alahmari, Saad Shutaywi, Meshal Althubiti, Sara A. Ahmadian, Ali Henan Univ Affiliated Hosp 1 Dept Oncol Kaifeng 475000 Henan Province Peoples R China AlMaarefa Univ Coll Appl Sci Dept Comp Sci & Informat Syst Riyadh 13713 Saudi Arabia Northern Border Univ Appl Coll Dept Comp Sci Ar Ar Saudi Arabia King Abdulaziz Univ Coll Sci & Arts Dept Math Rabigh Saudi Arabia Majmaah Univ Coll Comp & Informat Sci Dept Comp Sci Al Majmaah 11952 Saudi Arabia Istanbul Okan Univ Fac Engn & Nat Sci Istanbul Turkiye Jadara Univ Jadara Univ Res Ctr Irbid Jordan

The decision-making process in healthcare monitoring systems has extensively used deep learning and the Internet of Things (IoT). Among the new uses in today's procedures is disease prediction. A difficult challenge in computer-aided diagnosis (CAD) is lung cancer prediction, which is addressed in this paper's solution using deep learning and IoT. IoT medical devices send disease-related data to the server, as lung cancer is a hazardous medical condition that must be detected faster. Following processing, a multi-layer Convolutional neural Network (ML-CNN) model is used to classify the medical data into benign and malignant groups. Enhanced Particle swarm optimization (EPSO) is also used to enhance learning capacity (accuracy and loss). Medical data from the Internet of Medical Things (IoMT), including sensor data and Computed Tomography (CT) scan results, is used in this stage. The information from sensors and IoMT devices' picture data is collected for this purpose, and classification operations are then performed. The suggested method's accuracy, precision, sensitivity, specificity, F-score, and computation time are compared to well-known current approaches such as the Support Vector Machine (SVM), Probabilistic neural Network (PNN), and Convolutional neural Network (CNN). Linear Imaging and Self-Scanning Sensor (LISS) and Lung image Database Consortium (LIDC) datasets were the two lung datasets used for this performance evaluation. Trial results indicate that the recommended strategy may aid in the timely and accurate identification of lung cancer in radiologists compared to other techniques. The efficacy of the suggested ML-CNN was examined through Python analysis. The results showed that the accuracy was superior to the number of instances, the precision was superior to the number of cases, and the sensitivity was superior to several instances, the F-score was superior to the number of cases, the error rate was inferior to the number of cases, and the computat

关键词： Convolutional neural networks Enhanced particle swarm optimization Deep learning Internet of medical things Multi-layer convolutional neural network artificial intelligence Lung cancer detection

来源：评论

学校读者我要写书评

暂无评论

Supervised Spiking neural Network for SAR image Recognition: Analysis of Encoding Methods and Performance under Strong Noise Influence 12

Supervised Spiking Neural Network for SAR Image Recognition:...

引用

SPIE 12th International Symposium on Multispectral image processing and Pattern Recognition, MIPPR 2023

作者： Junyu, Wang Hao, Sun Tao, Tang Lin, Lei Kefeng, Ji National University of Defense Technology 109 Deya Road Kaifu District Hunan Changsha410003 China

ISBN: (数字)9781510675001

ISBN: (纸本)9781510674998

With the rapid development of artificial neural network (ANN), the field of synthetic aperture radar (SAR) target recognition has witnessed significant progress. However, due to the poor interpretability and ease of being affected by speckle noise, it brings challenges to ANN for SAR target recognition. Spiking neural Network (SNN) has emerged as the third-generation neural network architecture and presents promising prospects for various applications. This study aims to explore the performance of SNN in SAR target recognition. In our experiments, we achieved comparable performance to conventional neural networks by utilizing directly trained SNN. This indicates the effectiveness of SNN in coping with SAR target recognition tasks. Moreover, we investigated the impact of different spiking encoders on SAR target recognition. Specifically, we compared the performance of SNN using the Poisson encoder and utilizing the first layer of the SNN as an encoder. This comparison provides valuable insights into the optimal coding strategy for SNN-based SAR target recognition. Additionally, we examined the robustness of SNNs in the presence of strong speckle noise. Our findings demonstrate that SNN can maintain good performance under the influence of strong speckle noise. The outcomes of this research shed light on the potential of SNN as a powerful tool for SAR target recognition. Future studies can focus on exploring SNN's applicability to SAR Interpretation. © 2024 SPIE.

关键词： Synthetic aperture radar

来源：评论

学校读者我要写书评

暂无评论

MCT-Net: a multi-branch hybrid CNN-transformer model for medical image segmentation

引用

Pattern Analysis and applications 2025年第2期28卷 1-21页

作者： Shen, Longfeng Diao, Liangjin Peng, Rui Chen, Jiacong Lu, Zhengtian Ge, Fangzhen Anhui Engineering Research Center for Intelligent Computing and Application on Cognitive Behavior (ICACB) College of Computer Science and Technology Huaibei Normal University Anhui Huaibei China Institute of Artificial Intelligence Hefei Comprehensive National Science Center Hefei China Anhui Big-Data Research Center on University Management Huaibei Normal University Anhui Huaibei China

In recent years, neural networks have demonstrated substantial progress in medical image segmentation. However, accurately segmenting objects in medical images is often restricted by edge blurring, which complicates the delineation of structures of interest. The purpose of this study is to develop a multi-branch hybrid CNN-transformer model to address the issue of edge blurring in medical image segmentation. This approach enables more precise edge detection and segmentation. Integrating hybrid CNN and transformer decoders facilitates detailed recovery while preserving global structures, thus minimizing errors in regions with blurred edges. Additionally, we incorporate a hybrid attention mechanism at the model’s bottleneck to enhance feature transfer between the encoder and decoder. The model was trained using the ACDC, Synapse, and polyp datasets, with a focus on improving segmentation accuracy in regions with blurry edges. Experimental results reveal that the proposed model surpasses existing state-of-the-art methods on the ACDC, Synapse, and polyp datasets, demonstrating its superior performance and effectiveness. These results suggest that the proposed model offers a significant improvement in handling edge blurring, with potential applications in enhancing medical image analysis and diagnostics. © The Author(s), under exclusive licence to Springer-Verlag London Ltd., part of Springer Nature 2025.

关键词： Attention mechanism Convolutional neural network Edge information Medical image segmentation Transformer

来源：评论

学校读者我要写书评

暂无评论

Advanced Detection of Copy-Move Forgery Using Deep Convolutional neural Network Features Integrated with Machine Learning-Based Classification Techniques 3rd

Advanced Detection of Copy-Move Forgery Using Deep Convoluti...

引用

3rd International Conference on Machine Learning, Cloud Computing and Intelligent Mining, MLCCIM 2024

作者： Al-khuzaie, Mohammed Y. Chohan, Jasgurpreet Singh Sabah, Hawraa Ali Dey, Protyay Verma, Deeksha Hussein, Laith College of Technical Engineering National University of Science and Technology Dhi Qar Nasiriyah64001 Iraq School of Mechanical Engineering Rayat Bahra University Mohali India NIMS School of Computing Science and Artificial Intelligence NIMS University Rajasthan Rajasthan Jaipur India Department of Computer Science Engineering Chandigarh Engineering College Chandigarh Group of Colleges Jhanjeri- Punjab Mohali140307 India College of Technical Engineering The Islamic University Najaf Iraq

ISBN: (纸本)9789819624676

Technological advancements have significantly contributed to the creation and processing of digital images through various image manipulation software available today. Consequently, the need for effective image forgery detection techniques has become paramount to distinguish between authentic and manipulated images. image forensics is utilized in various fields, including national intelligence agencies, scientific publications, and social networks. One specific type of image manipulation, known as copy-move forgery, involves copying and pasting a portion of an image within the same image, resulting in an altered version of the original. In this study, we introduce a lightweight convolutional neural network (CNN) architecture combined with Support Vector Machine (SVM) classification for copy-move forgery detection (CMFD). This approach uses a similarity measure across feature patches to identify regions containing forgeries. We evaluated the effectiveness of our model using the challenging MICCF600 dataset commonly employed in CMFD research. The proposed model effectively reduces false positives, thereby enhancing pixel-level accuracy and reliability in CMFD applications. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

LesionAid: vision transformers-based skin lesion generation and classification – A practical review

引用

Multimedia Tools and applications 2025年 1-22页

作者： K, Mallikharjuna Rao Krishna, Ghanta Sai Supriya, Kundrapu Sorgile, Meetiksha Data Science and Artificial Intelligence International Institute of Information Technology Naya Raipur India Computer Science and Engineering International Institute of Information Technology Naya Raipur India

Skin cancer is one of the most prevalent forms of human cancer. It is recognized mainly visually, beginning with clinical screening and continuing with the dermoscopic examination, histological assessment, and specimen collection. Deep convolutional neural networks (CNNs) perform highly segregated and potentially universal tasks against a classified fine-grained object. This study suggests a novel multi-class prediction framework that uses ViT and ViTGAN to categories skin lesions. To address the class disparity, GANs (Generative Adversarial networks) based on vision transformers are used. The framework comprises four main phases: ViTGANs, image processing, and explainable AI. Phase 1 consists of generating synthetic images using ViTGAN to balance all the classes in the dataset. To enhance the amount of the data, the second phase involves using various morphological processes and data augmentation techniques. In phases three and four, a ViT model for edge computing systems that can recognize patterns and classify skin lesions from the user's skin that is visible in the picture is developed. In phase 3, after classifying the lesions into the desired class with ViT, we will use explainable AI (XAI) that leads to more explainable results (using activation maps, etc.) while ensuring high predictive accuracy. The results demonstrate that the model used for generating synthetic images has achieved an FID score of 13.32 and the ViT model has achieved 99.2% as its training accuracy and 97.4% as its validation accuracy. The whole framework is compared with the existing frameworks for skin lesion detection. And explainable AI (XAI) is used in the proposed framework in order to increase model transparency and boost trust among users by illustrating the main factors affecting predictions. This interpretability helps physicians in making more informed decisions by providing clear insights into the model's reasoning. © The Author(s), under exclusive licence to Springer Science+Bu

关键词： Generative adversarial networks

来源：评论

学校读者我要写书评

暂无评论

Electron Imaging Reconstruction for Pixelated Semiconductor Tracking Detectors in Transmission Electron Microscopes Using the Approach of Convolutional neural networks

引用

IEEE TRANSACTIONS ON NUCLEAR SCIENCE 2022年第5期69卷 1014-1021页

作者： Eckert, Bjorn Aschauer, Stefan Holl, Peter Majewski, Petra Zabel, Thomas Strueder, Lothar PNSensor GmbH D-81739 Munich Germany Univ Siegen Dept Phys D-57068 Siegen Germany

Energetic electrons of several hundred-kilo electron volts (keV) as used in transmission electron microscopy applications do not deposit their energy completely at their point of entry (PoE). Instead, in a detector with a thickness of 450 mu m, they produce randomly 3-D tracks often extending over many pixels. The length and the shape of these tracks strongly depend on the primary energy of the electrons. Statistically, an electron deposits most of its energy at the end of its track. The output of a tracking detector system is the pixelated 2-D projection of the energy deposition. The proposed convolutional neural network (CNN) is capable of performing a frame-based event analysis and PoE reconstruction. The resulting modulation transfer function (MTF) is 0.77 at a Nyquist frequency of 0.5 obtained from a slanted edge. It is based on a U-net with a specially designed loss function using the confusion matrix. The input data to the CNN only need to be offset corrected. The output of the CNN is a PoE map containing the probability of a PoE of an electron for each pixel and frame. The architecture of the designed CNN also allows reconstructing different frame sizes without retraining the network.

关键词： artificial intelligence charge-coupled image sensors data analysis electron detectors image processing neural networks semiconductor detectors

来源：评论

学校读者我要写书评

暂无评论

A Survey of Deep Learning Techniques and applications in Bioengineering: A Latin American Perspective 24th

A Survey of Deep Learning Techniques and Applications in Bio...

引用

24th Argentinian Congress of Bioengineering (SABI) / 13th Clinical Engineering Conference (SABI)

作者： Comas, Diego S. Meschino, Gustavo J. Amalfitano, Agustin Iturriaga, Juan I. Ballarin, Virginia L. Natl Univ Mar del Plata Image Proc Lab Inst Sci & Technol Res Elect ICyTE CONICET Mar Del Plata Argentina Consejo Nacl Invest Cient & Tecn Mar Del Plata Argentina Natl Univ Mar del Plata Bioengn Lab Inst Sci & Technol Res Elect ICyTE CONICET Mar Del Plata Argentina

ISBN: (纸本)9783031619595;9783031619601

The rapid advancement of new paradigms in artificial intelligence has had a profound impact on scientific research in recent years. The field of medical data and its applications in healthcare have particularly benefited from these advancements, rising the quality of diagnoses, treatment effectiveness, and knowledge extraction. Deep learning has revolutionized the concept of data, including images, videos, text, and signals. Convolutional neural networks and sequential models have played a significant role in feature extraction and classification of biomedical images and signals, enabling powerful diagnostic assistance. Generative models have further expanded the artificial intelligence capabilities, allowing the generation of realistic images and sequences. Attention mechanisms and Transformers have revolutionized the field, pushing the boundaries of the applications. Despite these advancements, accessibility to these technologies remains a challenge, especially in less developed countries where computational resources are limited. This paper provides a review of deep-learning applications in Bioengineering, focusing on the works of researchers from Latin America. It explores the types of applications and technologies during the period 2021 to 2023, which witnessed unprecedented advancements. Even with these limitations, there has been significant and high-quality production and progresses. However, efforts are required to ensure these technologies can benefit researchers and practitioners worldwide.

关键词： artificial Intelligence deep learning medical imaging feature extraction bio-medical signals image processing generative models accessibility transfer learning Latin America

来源：评论

学校读者我要写书评

暂无评论

Deep Learning Based Medical image Segmentation in Prenatal Prediction of Neurodevelopmental Disorders 2

Deep Learning Based Medical Image Segmentation in Prenatal P...

引用

2nd IEEE International Conference on Communication, Security and artificial Intelligence, ICCSAI 2023

作者： Vetriselvi, D. Thenmozhi, R. School of Computing Srm Institute of Science and Technology Department of Computing Technologies Chennai Kattankulathur India

ISBN: (纸本)9798350369960

The onset of autism related neurodevelopmental disorders happening in the embryonic stage itself. The effectiveness of treatment is greatly dependent on the early detection. Deep learning has made significant strides in the field of artificial intelligence. To perform semantic segmentation on the ultrasound image of the developing embryo, this research attempts to design a framework based on 3D Convolutional neural Network, a deep learning model. The segments of the fetal brain can be more effectively separated by combining many convolutional neural networks with different configurations. Transfer learning can be used to lessen the paucity of data by using pretrained models. Two CNNs with different configurations can process a single image, and fusion is used to integrate the two feature maps. The normalization of the image takes place as a pre-processing step. The performance is measured with the evaluation parameters loss, training accuracy and testing accuracy. © 2023 IEEE.

关键词： AlexNet Autism Spectrum Disorders Convolutional neural Network Deep Learning Dual Channel Convolutional neural Network Segmentation Transfer Learning

来源：评论

学校读者我要写书评

暂无评论

Countering Adversarial Zeroth Order Optimization Attacks Based on neural-Cleanse, Gaussian and Poisson Noise Adding

Countering Adversarial Zeroth Order Optimization Attacks Bas...

引用

2024 International Conference on Industrial Engineering, applications and Manufacturing, ICIEAM 2024

作者： Kotenko, Igor Saenko, Igor Sadovnikov, Vladimir Laboratory Of Computer Security Problems Saint-Petersburg Russia

ISBN: (纸本)9798350395013

Nowadays, machine learning is becoming an increasingly widely used artificial intelligence technology and is being actively implemented in various fields of science and technology, such as defense against cyber attacks, image recognition, computer vision, autonomous vehicles and other complex tasks. However, despite the benefits of machine learning, it attracts the attention of attackers. Cyberattacks against machine learning models, such as classifiers or artificial neural networks, can seriously distort the results of these models and cause irreversible damage to machine learning-based decision-making systems. Therefore, research aimed at countering cyber attacks using machine learning models is becoming very important nowadays. The paper presents a method for protecting against adversarial attacks, Zeroth Order Optimization (ZOO), which is based on the use of neural-Cleanse technology and the addition of Gaussian and Poisson noise. The proposed approach is aimed at increasing the resistance of neural networks to malicious attacks by additional processing of input data and complicating the optimization problem for attackers. An experimental evaluation of the proposed approach was carried out on the PC Parts images Dataset using the K-Nearest Neighbors, Random Forest, Naive Bayes Classifier, and Decision Trees classifiers. The study results showed the high efficiency of the proposed approach to protecting models from the effects of adversarial ZOO attacks. The findings may be useful for developing more reliable systems and improving security in the field of machine learning. © 2024 IEEE.

关键词： Network security

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：