检索结果-内蒙古大学图书馆

Multi-Scale Spatio-Temporal Memory Network for Lightweight Video Denoising

ieee TRANSACTIONS ON image processing 2024年 33卷 5810-5823页

作者： Sun, Lu Wu, Fangfang Ding, Wei Li, Xin Lin, Jie Dong, Weisheng Shi, Guangming Xidian Univ Sch Artificial Intelligence Xian 710048 Peoples R China Xidian Univ Sch Comp Sci & Technol Xian 710071 Peoples R China West Virginia Univ Lane Dept Comp Sci & Elect Engn Morgantown WV 26506 USA

Deep learning-based video denoising methods have achieved great performance improvements in recent years. However, the expensive computational cost arising from sophisticated network design has severely limited their applications in real-world scenarios. To address this practical weakness, we propose a multiscale spatio-temporal memory network for fast video denoising, named MSTMN, aiming at striking an improved trade-off between cost and performance. To develop an efficient and effective algorithm for video denoising, we exploit a multiscale representation based on the Gaussian-Laplacian pyramid decomposition so that the reference frame can be restored in a coarse-to-fine manner. Guided by a model-based optimization approach, we design an effective variance estimation module, an alignment error estimation module and an adaptive fusion module for each scale of the pyramid representation. For the fusion module, we employ a reconstruction recurrence strategy to incorporate local temporal information. Moreover, we propose a memory enhancement module to exploit the global spatio-temporal information. Meanwhile, the similarity computation of the spatio-temporal memory network enables the proposed network to adaptively search the valuable information at the patch level, which avoids computationally expensive motion estimation and compensation operations. Experimental results on real-world raw video datasets have demonstrated that the proposed lightweight network outperforms current state-of-the-art fast video denoising algorithms such as FastDVDnet, EMVD, and ReMoNet with fewer computational costs.

关键词： Noise reduction Streaming media Noise measurement Estimation computational modeling Motion estimation Noise Memory management image restoration image denoising Video denoising lightweight multiscale model-guided spatio-temporal memory enhancement

来源：评论

学校读者我要写书评

暂无评论

Visual Communication image Clarity processing System on the Basis of Artificial intelligence 2

Visual Communication Image Clarity Processing System on the ...

引用

2nd International Conference on Data Science and Information System, ICDSIS 2024

作者： Gao, Shuang School Of Fine Arts And Design Changchun Humanities And Sciences College Jilin Changchun China

ISBN: (纸本)9798350381665

Traditional visual communication image processing is done manually, which is not only time-consuming and labor-intensive, but also not very effective. Therefore, this article adopted an AI (Artificial intelligence) based visual communication image clarity processing system. The main functional modules of the system include four aspects: visual transmission of image data acquisition based on AI, adjustment of basic image parameters, image dehazing processing, and image clarity enhancement. Among them, image clarity was a complete functional module and the core of the entire image clarity processing system. This article intended to take large-scale image data as an example to analyze the computational speed and stability of the effectiveness of this method, in order to verify its practicality. The processing time for 100 images was 0.8 seconds, with a standard deviation of 0.025 for clarity improvement and 0.030 for naturalness improvement. This system is beneficial for improving the clarity of visual communication images and reducing image processing time. © 2024 ieee.

关键词： Artificial intelligence

来源：评论

学校读者我要写书评

暂无评论

CBANet: Toward Complexity and Bitrate Adaptive Deep image Compression Using a Single Network

引用

ieee TRANSACTIONS ON image processing 2023年 32卷 2049-2062页

作者： Guo, Jinyang Xu, Dong Lu, Guo Beihang Univ Inst Artificial Intelligence State Key Lab Software Dev Environm Beijing 100191 Peoples R China Univ Hong Kong Dept Comp Sci Hong Kong Peoples R China Shanghai Jiao Tong Univ Inst Image Commun & Network Engn Shanghai 200240 Peoples R China

In this work, we propose a new deep image compression framework called Complexity and Bitrate Adaptive Network (CBANet) that aims to learn one single network to support variable bitrate coding under various computational complexity levels. In contrast to the existing state-of-the-art learning-based image compression frameworks that only consider the rate-distortion trade-off without introducing any constraint related to the computational complexity, our CBANet considers the complex rate-distortion-complexity trade-off when learning a single network to support multiple computational complexity levels and variable bitrates. Since it is a non-trivial task to solve such a rate-distortion-complexity related optimization problem, we propose a two-step approach to decouple this complex optimization task into a complexity-distortion optimization sub-task and a rate-distortion optimization sub-task, and additionally propose a new network design strategy by introducing a Complexity Adaptive Module (CAM) and a Bitrate Adaptive Module (BAM) to respectively achieve the complexity-distortion and rate-distortion trade-offs. As a general approach, our network design strategy can be readily incorporated into different deep image compression methods to achieve complexity and bitrate adaptive image compression by using a single network. Comprehensive experiments on two benchmark datasets demonstrate the effectiveness of our CBANet for deep image compression. Code is released at https://***/JinyangGuo/CBANet-release.

关键词： image coding Bit rate Decoding computational complexity computational modeling Adaptive systems Rate-distortion Deep learning image compression variable bitrate coding dynamic computational complexity

来源：评论

学校读者我要写书评

暂无评论

ADDRESSING ARTEFACTS IN ANATOMICAL MR imageS: A K-SPACE-BASED APPROACH 21

ADDRESSING ARTEFACTS IN ANATOMICAL MR IMAGES: A K-SPACE-BASE...

引用

21st ieee International symposium on Biomedical Imaging (ISBI)

作者： Boudissa, Selma Kanli, Georgia Perlo, Daniele Jaquet, Thomas Keunen, Olivier Luxembourg Inst Hlth Translat Radiom Luxembourg Luxembourg Luxembourg Inst Hlth In Vivo Imaging Platform Luxembourg Luxembourg

ISBN: (纸本)9798350313345;9798350313338

Magnetic Resonance Imaging (MRI) is a valuable tool in medical diagnosis and treatment planning. Acquired data can be affected by various artefacts that can compromise image quality and result in decreased diagnostic accuracy. Artificial intelligence emerged as a robust solution in enhancing the quality of images. In the context of anatomical MRI data, we have chosen to use Deep Learning (DL) models to correct the artefacts and improve the quality of MR images. In this work we propose a library that simulates realistic primary artefacts by manipulating the k-space signal(1), using standard image processing techniques. Our investigation focuses on three artefacts commonly encountered in anatomical images: Gaussian noise, blur effect and Motion Artefact (MA) with varying levels of degradation. We trained DL models to learn the artefacts features, correct them and improve the quality of the MR images. The dataset consists of in vivo 2D anatomical mouse brain images acquired on a 3T MRI system. The results of this study confirm the performance of deep learning models in the field of artefacts correction of medical images with quality improvement. The proposed method surpassed the classical denoising approach by 14.46% in terms of quality metrics and exhibited a 82.73% improvement for the deblurring task. The model performed well in the application of MA correction without any consensus image processing method has been established.

关键词： magnetic resonance image artefacts image processing k-space deep learning

来源：评论

学校读者我要写书评

暂无评论

Single-Node Power Demand During AI Training: Measurements on an 8-GPU NVIDIA H100 System

引用

ieee ACCESS 2025年 13卷 61740-61747页

作者： Latif, Imran Newkirk, Alex C. Carbone, Matthew R. Munir, Arslan Lin, Yuewei Koomey, Jonathan Yu, Xi Dong, Zhihua Brookhaven Natl Lab Comp & Data Sci Directorate Upton NY 11973 USA Lawrence Berkeley Natl Lab Bldg Technol & Urban Syst Berkeley CA 94720 USA Florida Atlantic Univ Dept Elect Engn & Comp Sci Boca Raton FL 33431 USA Koomey Analyt San Francisco CA 94011 USA

The expansion of artificial intelligence (AI) applications has driven substantial investment in computational infrastructure, especially by cloud computing providers. Quantifying the energy footprint of this infrastructure requires models parameterized by the power demand of AI hardware during training. In this work, we measured the instantaneous power draw of an 8-GPU NVIDIA H100 HGX node during the training of open-source image classifier (ResNet) and large-language models (Llama2-13b). We characterize power demand for a single node configuration, providing foundational data for future multi-node studies. The maximum observed power draw was approximately 8.4 kW, 18% lower than the manufacturer-rated 10.2 kW, even with GPUs near full utilization. Holding model architecture constant, increasing batch size from 512 to 4096 images for ResNet reduced total training energy consumption by a factor of 4. These findings can inform capacity planning for data center operators and energy use estimates by researchers. Future work will investigate the impact of cooling technology and carbon-aware scheduling on AI workload energy consumption.

关键词： Artificial intelligence Training Hardware Power measurement Graphics processing units Power demand Benchmark testing Visualization Stress computational modeling AI training sustainable computing GPU power measurements large language models

来源：评论

学校读者我要写书评

暂无评论

Chest-Diffusion: A Light-Weight Text-to-image Model for Report-to-CXR Generation 21

Chest-Diffusion: A Light-Weight Text-to-Image Model for Repo...

引用

21st ieee International symposium on Biomedical Imaging (ISBI)

作者： Huang, Peng Gao, Xue Huang, Lihong Jiao, Jing Li, Xiaokang Wang, Yuanyuan Guo, Yi Fudan Univ Dept Elect Engn Shanghai 200433 Peoples R China Key Lab Med Imaging Comp & Comp Assisted Interven Shanghai 200032 Peoples R China

ISBN: (纸本)9798350313345;9798350313338

Text-to-image generation has important implications for generation of diverse and controllable images. Several attempts have been made to adapt Stable Diffusion (SD) to the medical domain. However, the large distribution difference between medical reports and natural texts, as well as high computational complexity in common stable diffusion limit the authenticity and feasibility of the generated medical images. To solve above problems, we propose a novel light-weight transformer-based diffusion model learning framework, Chest-Diffusion, for report-to-CXR generation. Chest-Diffusion employs a domainspecific text encoder to obtain accurate and expressive text features to guide image generation, improving the authenticity of the generated images. Meanwhile, we introduce a light-weight transformer architecture as the denoising model, reducing the computational complexity of the diffusion model. Experiments demonstrate that our Chest-Diffusion achieves the lowest FID score 24.456, under the computation budget of 118.918 GFLOPs, which is nearly one-third of the computational complexity of SD.

关键词： Chest X-ray Diffusion model Text-to-image generation CLIP Vision Transformer

来源：评论

学校读者我要写书评

暂无评论

The System Operates by Capturing images of the Wall Surface and Applying Advanced image processing Algorithms to Analyze the Visual Data 18

The System Operates by Capturing Images of the Wall Surface ...

引用

18th International Joint symposium on Artificial intelligence and Natural Language processing (ISAI-NLP) / 4th International Conference on Artificial intelligence and Internet of Things (AIoT)

作者： Suksangaram, Wiwit Yimyam, Worawut Phetchaburi Rajabhat Univ Dept Business Informat Management Phetchaburi Thailand

ISBN: (纸本)9798350371215

The main objective of this research is to leverage data and image processing technology to develop a system capable of detecting cracks in walls. The system aims to provide users with a convenient and user-friendly solution by utilizing principles from app development, enabling them to capture photos and assess the presence of wall cracks. To achieve this objective, various image processing techniques are employed, including the use of a Gaussian kernel, grayscale conversion, Sobel edge detection, and thresholding. These techniques are implemented using the Python programming language to develop and apply the image processing algorithms specifically designed for wall crack detection. By employing these techniques, the system can accurately identify cracks and assess the extent of damage in a house using preliminary data. The developed system offers significant advantages for potential homebuyers as it aids in assessing necessary repairs before making a purchase decision. By providing users with a tool to detect and evaluate wall cracks, they can make informed choices regarding the condition of the property and estimate the potential repair costs. This research aims to enhance the accuracy and efficiency of assessing wall cracks, ultimately benefiting individuals in their decision-making process when considering a property purchase.

关键词： Wall Surface Kernal image processing Algorithms

来源：评论

学校读者我要写书评

暂无评论

Efficient processing of Spiking Neural Networks via Task Specialization

引用

ieee TRANSACTIONS ON EMERGING TOPICS IN computational intelligence 2024年第5期8卷 3603-3613页

作者： Abu Lebdeh, Muath Yildirim, Kasim Sinan Brunelli, Davide Univ Trento Dept Informat Engn & Comp Sci I-38122 Trento Italy Univ Trento Dept Ind Engn I-38122 Trento Italy

Spiking neural networks (SNNs) are considered as a candidate for efficient deep learning systems: these networks communicate with 0 or 1 spikes and their computations do not require the multiply operation. On the other hand, SNNs still have large memory overhead and poor utilization of the memory hierarchy;powerful SNN has large memory requirements and requires multiple inference steps with dynamic memory patterns. This paper proposes performing the image classification task as collaborative tasks of specialized SNNs. This specialization allows us to significantly reduce the number of memory operations and improve the utilization of memory hierarchy. Our results show that the proposed approach improves the energy and latency of SNNs inference by more than 10x. In addition, our work shows that designing narrow (and deep) SNNs is computationally more efficient than designing wide (and shallow) SNNs.

关键词： Neurons Memory management Task analysis Membrane potentials Encoding Training computational modeling Spiking neural networks low energy and latency computing memory aware SNNs specialized SNNs

来源：评论

学校读者我要写书评

暂无评论

Mosaic-Mixed Attention-Based Unexpected Traffic Scene Classification

引用

ieee ACCESS 2025年 13卷 15712-15722页

作者： Lee, Sang-Hyun Lee, Soomok Yun, Ilsoo Ajou Univ Dept Data Network & AI Suwon 16499 South Korea Ajou Univ Dept Mobil Engn Suwon 16499 South Korea Ajou Univ Dept Transportat Syst Engn Suwon 16499 South Korea

With the rapid advancements in artificial intelligence and smart mobility technologies, traffic monitoring systems are evolving quickly. Among these systems, in-vehicle monitoring systems using Object Detection (OD) algorithms are gaining attention for identifying traffic participants in distress. However, current OD algorithms often underperform in complex or unexpected traffic scenarios, such as accidents. In this study, we propose a novel scene classification network that integrates OD with a cross-attention mechanism By leveraging spatial mosaic and mixed attention mechanisms, the network emphasizes spatial relationships and inter-channel correlations, significantly enhancing accuracy in identifying critical traffic events. The detailed evaluation demonstrates improved efficiency and accuracy, underscoring the potential of the system for future traffic incident classification.

关键词： Accidents Feature extraction Roads Classification algorithms Attention mechanisms Accuracy computational modeling Cameras Scene classification Convolutional neural networks Traffic monitoring scene classification attention network image mosaic processing

来源：评论

学校读者我要写书评

暂无评论

Simpler Gradient Methods for Blind Super-Resolution With Lower Iteration Complexity

引用

ieee TRANSACTIONS ON SIGNAL processing 2024年 72卷 5123-5139页

作者： Li, Jinsheng Cui, Wei Zhang, Xu Beijing Inst Technol Sch Informat & Elect Beijing 100081 Peoples R China Xidian Univ Sch Artificial Intelligence Key Lab Collaborat Intelligence Syst Minist Educ Xian 710126 Peoples R China Xidian Univ Sch Artificial Intelligence Key Lab Intelligent Percept & Image Understanding Minist Educ Xian 710126 Peoples R China

We study the problem of blind super-resolution, which can be formulated as a low-rank matrix recovery problem via vectorized Hankel lift (VHL). The previous gradient descent method based on VHL named PGD-VHL relies on additional regularization such as the projection and balancing penalty, exhibiting a suboptimal iteration complexity. In this paper, we propose a simpler unconstrained optimization problem without the above two types of regularization and develop two new and provable gradient methods named VGD-VHL and ScalGD-VHL. A novel and sharp analysis is provided for the theoretical guarantees of our algorithms, which demonstrates that our methods offer lower iteration complexity than PGD-VHL. In addition, ScalGD-VHL has the lowest iteration complexity while being independent of the condition number. Furthermore, our novel analysis reveals that the blind super-resolution problem is less incoherence-demanding, thereby eliminating the necessity for incoherent projections to achieve linear convergence. Empirical results illustrate that our methods exhibit superior computational efficiency while achieving comparable recovery performance to prior arts.

关键词： Superresolution Complexity theory Convergence Minimization Gradient methods Signal processing algorithms Sensors Optimization Vectors Radar imaging Blind super-resolution vanilla gradient descent scaled gradient descent low-rank matrix factorization

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：