检索结果-内蒙古大学图书馆

encoder-decoder networks for Analyzing Thermal and Power Delivery networks

ACM TRANSACTIONS ON DESIGN AUTOMATION OF ELECTRONIC SYSTEMS 2023年第1期28卷 1-27页

作者： Chhabria, Vidya A. Ahuja, Vipul Prabhu, Ashwath Patil, Nikhil Jain, Palkesh Sapatnekar, Sachin S. Univ Minnesota 200 Union St SE Minneapolis MN 55455 USA Qualcomm Technol Inc Carina West Tower Marathalli Outer Ring Rd Doddan Bengaluru 560037 Karnataka India

Power delivery network (PDN) analysis and thermal analysis are computationally expensive tasks that are essential for successful integrated circuit (IC) design. Algorithmically, both these analyses have similar computational structure and complexity as they involve the solution to a partial differential equation of the same form. This article converts these analyses into image-to-image and sequence-to-sequence translation tasks, which allows leveraging a class of machine learning models with an encoder-decoder-based generative (EDGe) architecture to address the time-intensive nature of these tasks. For PDN analysis, we propose two networks: (i) IREDGe: a full-chip static and dynamic IR drop predictor and (ii) EMEDGe: electromigration (EM) hotspot classifier based on input power, power grid distribution, and power pad distribution patterns. For thermal analysis, we propose ThermEDGe, a full-chip static and dynamic temperature estimator based on input power distribution patterns for thermal analysis. These networks are transferable across designs synthesized within the same technology and packing solution. The networks predict on-chip IR drop, EM hotspot locations, and temperature in milliseconds with negligibly small errors against commercial tools requiring several hours.

关键词： Machine learning (ML) for electronic design automation (EDA) Thermal analysis Power delivery network (PDN) analysis IR drop electromigration (EM) encoder-decoder networks U-Nets

来源：评论

学校读者我要写书评

暂无评论

Uncertainty quantification for goal-oriented inverse problems via variational encoder-decoder networks

引用

INVERSE PROBLEMS 2024年第7期40卷 075010-075010页

作者： Afkham, Babak Maboudi Chung, Julianne Chung, Matthias Tech Univ Denmark Dept Appl Math & Comp Sci DTU Compute Lyngby Denmark Emory Univ Dept Math Atlanta GA 30322 USA

In this work, we describe a new approach that uses variational encoder-decoder (VED) networks for efficient uncertainty quantification for goal-oriented inverse problems. Contrary to standard inverse problems, these approaches are goal-oriented in that the goal is to estimate some quantities of interest (QoI) that are functions of the solution of an inverse problem, rather than the solution itself. Moreover, we are interested in computing uncertainty metrics associated with the QoI, thus utilizing a Bayesian approach for inverse problems that incorporates the prediction operator and techniques for exploring the posterior. This may be particularly challenging, especially for nonlinear, possibly unknown, operators and nonstandard prior assumptions. We harness recent advances in machine learning, i.e. VED networks, to describe a data-driven approach to large-scale inverse problems. This enables a real-time uncertainty quantification for the QoI. One of the advantages of our approach is that we avoid the need to solve challenging inversion problems by training a network to approximate the mapping from observations to QoI. Another main benefit is that we enable uncertainty quantification for the QoI by leveraging probability distributions in the latent and target spaces. This allows us to efficiently generate QoI samples and circumvent complicated or even unknown forward models and prediction operators. Numerical results from medical tomography reconstruction and nonlinear hydraulic tomography demonstrate the potential and broad applicability of the approach.

关键词： deep learning regularization encoder-decoder networks uncertainty quantification quantity of interest hyperparameter selection

来源：评论

学校读者我要写书评

暂无评论

Learning From Architectural Redundancy: Enhanced Deep Supervision in Deep Multipath encoder-decoder networks

引用

IEEE TRANSACTIONS ON NEURAL networks AND LEARNING SYSTEMS 2022年第9期33卷 4271-4284页

作者： Luo, Ying Lu, Jinhu Jiang, Xiaolong Zhang, Baochang Beihang Univ Sch Automat Sci & Elect Engn Beijing 100191 Peoples R China Beihang Univ Shenyuan Honors Coll Beijing 100191 Peoples R China Beihang Univ Sch Automat Sci & Elect Engn State Key Lab Software Dev Environm Beijing 100191 Peoples R China Beihang Univ Beijing Adv Innovat Ctr Big Data & Brain Comp Beijing 100191 Peoples R China Alibaba Grp Beijing 100102 Peoples R China Beihang Univ Inst Artificial Intelligence Beijing 100191 Peoples R China

Deep encoder-decoders are the model of choice for pixel-level estimation due to their redundant deep architectures. Yet they still suffer from the vanishing supervision information issue that affects convergence because of their overly deep architectures. In this work, we propose and theoretically derive an enhanced deep supervision (EDS) method which improves on conventional deep supervision (DS) by incorporating variance minimization into the optimization. A new structure variance loss is introduced to build a bridge between deep encoder-decoders and variance minimization, and provides a new way to minimize the variance by forcing different intermediate decoding outputs (paths) to reach an agreement. We also design a focal weighting strategy to effectively combine multiple losses in a scale-balanced way, so that the supervision information is sufficiently enforced throughout the encoder-decoders. To evaluate the proposed method on the pixel-level estimation task, a novel multipath residual encoder is proposed and extensive experiments are conducted on four challenging density estimation and crowd counting benchmarks. The experimental results demonstrate the superiority of our EDS over other paradigms, and improved estimation performance is reported using our deeply supervised encoder-decoder.

关键词： Estimation Task analysis Decoding Optimization Redundancy Computer architecture Semantics Convolutional neural networks (CNN) crowd counting deep supervised learning encoder-decoder networks

来源：评论

学校读者我要写书评

暂无评论

Concrete roadway crack segmentation using encoder-decoder networks with range images

引用

AUTOMATION IN CONSTRUCTION 2020年 120卷

作者： Zhou, Shanglian Song, Wei Univ Alabama Dept Civil Construct & Environm Engn Tuscaloosa AL 35487 USA

Recently, researchers have utilized DCNN for pixel-wise crack classification through semantic segmentation. Nevertheless, some issues in current DCNN-based roadway crack segmentation are yet to be fully addressed. For example, image pre-processing techniques are often required to eliminate the surface variations in range images, which may bring uncertainties due to subjective parameter selection;besides, disturbances from many non-crack patterns such as pavement grooves can deteriorate the crack segmentation performance, which remains a challenge for current DCNN-based methodologies. This paper proposes a methodology based on encoder-decoder networks to achieve pixel-wise crack classification performance on laser-scanned range images, under the disturbance of surface variations and grooved patterns in concrete pavements. The raw range data is directly applied in this methodology without any pre-processing. A comparative study is performed to determine the optimal architecture layout among twelve proposed candidates. Meanwhile, the influence of residual connections on DCNN performance is investigated and demonstrated.

关键词： Deep convolutional neural network encoder-decoder networks Residual connection Range image Crack segmentation Pavement groove

来源：评论

学校读者我要写书评

暂无评论

Timber Tracing with Multimodal encoder-decoder networks 18th

Timber Tracing with Multimodal Encoder-Decoder Networks

引用

18th international Conference on Computer Analysis of Images and Patterns (CAIP)

作者： Zolotarev, Fedor Eerola, Tuomas Lensu, Lasse Kalviainen, Heikki Haario, Heikki Heikkinen, Jere Kauppi, Tomi Lappeenranta Lahti Univ Technol LUT Sch Engn Sci Dept Computat & Proc Engn Machine Vis & Pattern Recognit Lab POB 20 Lappeenranta 53851 Finland Finnos Oy Tukkikatu 5 Lappeenranta 53900 Finland

ISBN: (纸本)9783030298913;9783030298906

Tracking timber in the sawmill environment from the raw material (logs) to the end product (boards) provides various benefits including efficient process control, the optimization of sawing, and the prediction of end-product quality. In practice, the tracking of timber through the sawmilling process requires a methodology for tracing the source of materials after each production step. The tracing is especially difficult through the actual sawing step where a method is needed for identifying from which log each board comes from. In this paper, we propose an automatic method for board identification (board-to-log matching) using the existing sensors in sawmills and multimodal encoder-decoder networks. The method utilizes point clouds from laser scans of log surfaces and grayscale images of boards. First, log surface heightmaps are generated from the point clouds. Then both the heightmaps and board images are converted into "barcode" images using convolutional encoder-decoder networks. Finally, the "barcode" images are utilized to find matching logs for the boards. In the experimental part of the work, different encoder-decoder architectures were evaluated and the effectiveness of the proposed method was demonstrated using challenging data collected from a real sawmill.

关键词： Convolutional neural networks encoder-decoder networks Multimodal translation Machine vision Sawmilling

来源：评论

学校读者我要写书评

暂无评论

A DEEP encoder-decoder networks FOR JOINT DEBLURRING AND SUPER-RESOLUTION

A DEEP ENCODER-DECODER NETWORKS FOR JOINT DEBLURRING AND SUP...

引用

IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)

作者： Zhang, Xinyi Wang, Fei Dong, Hang Guo, Yu Xi An Jiao Tong Univ Inst Artificial Intelligence & Robot Xian Shaanxi Peoples R China

ISBN: (纸本)9781538646588

In this paper, we propose an end-to-end convolution neural network (CNN) to restore a clear high-resolution image from a severely blurry image. It's a highly ill-posed problem and brings tremendous challenges to state-of-art deblurring or super-resolution (SR) methods. A straightforward way to solve this problem is to concatenate two types of networks directly. However, experiments show that the concatenation of independent networks increases computation complexity instead of generating satisfying high-resolution images. Consequently, we focus on designing a single deep network to solve the deblurring and SR problems in parallel. Our method, called ED-DSRN, extends the traditional Super-Resolution network by adding a deblurring branch that shares the same feature maps extracted from an encoder-decoder module with the original SR branch. Extensive experiments show that our method produces remarkable deblurred and super-resolved images simultaneously with high efficiency.

关键词： Super-Resolution Blind deblurring Joint tasks encoder-decoder networks Parallel branches

来源：评论

学校读者我要写书评

暂无评论

A Deep encoder-decoder networks for Joint Deblurring and Super-Resolution

A Deep Encoder-Decoder Networks for Joint Deblurring and Sup...

引用

IEEE International Conference on Acoustics, Speech and Signal Processing

作者： Xinyi Zhang Fei Wang Hang Dong Yu Guo Institute of Artificial Intelligence and Robotics Xi'an Jiaotong University China

ISBN: (纸本)9781538646595

关键词： Super-Resolution Blind deblurring Joint tasks encoder-decoder networks Parallel branches

来源：评论

学校读者我要写书评

暂无评论

Anchor Ball Regression Model for large-scale 3D skull landmark detection

引用

NEUROCOMPUTING 2024年 567卷

作者： He, Tao Xu, Guikun Cui, Li Tang, Wei Long, Jie Guo, Jixiang Sichuan Univ Coll Comp Sci Machine Intelligence Lab Chengdu 610065 Peoples R China West China Hosp Stomatol Dept Oral & Maxillofacial Surg Chengdu 610041 Peoples R China Army Med Univ Daping Hosp Dept Oral & Maxillofacial Surg Chongqing 400042 Peoples R China

Recent deep learning models have exhibited impressive performance in the area of 3D skull landmark detection, but most of them aimed to detect a fixed number of landmarks. This paper focuses on automatically detecting an arbitrary number of landmarks on CT volumes, which meets the real clinical needs. To achieve robust performance for detecting arbitrary molar landmarks, we propose a novel 3D landmark detection model named Anchor Ball Regression Model (ABRM), which combines landmark detection and landmark classification losses for network training. For landmark detection, a novel landmark regression loss is proposed by predicting offsets to anchor balls instead of directly predicting landmarks. For landmark classification, an online hard negative mining loss is used to reduce absent landmarks' learning errors, and a small regularization constraint loss is performed for voxels outside the anchor balls. The network backbone of ABRM is obtained by manually pruning popular 3D-CNNs. We also present an available large-scale benchmark dataset in this paper, which, to the best of our knowledge, is the largest dataset for 3D skull landmark detection. The dataset comprises of 658 CT volumes, with 14 landmarks labeled by two junior and one senior doctors. The ABRM presents a good robust performance and outperforms other models on this dataset. The codes and dataset are accessible at https://***/ithet1007/mmld_code.

关键词： encoder-decoder networks 3D skull landmark detection CT volumes

来源：评论

学校读者我要写书评

暂无评论

Creating an AI fashioner through deep learning and computer vision

引用

EVOLVING SYSTEMS 2024年第3期15卷 717-729页

作者： Balim, Caner Ozkan, Kemal Afyon Kocatepe Univ Sandikli Vocat Sch Higher Educ Dept Comp Comp Programming Afyonkarahisar Turkiye Eskisehir Osmangazi Univ Fac Engn & Architecture Dept Comp Engn Eskisehir Turkiye

Fashion is a multibillion-dollar industry that concerns many people both socially and culturally. Thanks to social networks, there is a lot of data about the fashion industry on the internet. This has led researchers to shift their attention to this area, especially recently. This paper proposes an end-to-end framework to build an AI fashioner that can diagnose clothing compatibility and generate recommendations to improve compatibility. First, fashion compatibility reviews are analyzed, and incompatible clothing items are identified for each outfit combination. Next, the items of clothing that make up the outfit combination are separated using Mask R-CNN. Then, the incompatible clothing items were removed from the outfit combination, and the most similar outfit combinations were identified among the compatible clothing items. In addition, an attribute detection network was developed to extract the attributes of compatible outfits with the same category in the detected compatible outfits. Finally, recommendation sentences are generated using the detected attributes, and encoder-decoder models are used to train a deep network that generates recommendations from clothing images. Extensive experiments based on existing datasets demonstrate the effectiveness of the proposed method.

关键词： Outfit recommendation encoder-decoder networks Outfit segmentation Image captioning Image processing

来源：评论

学校读者我要写书评

暂无评论

Learning and Adaptation From Minimum Samples With Heterogeneous Quality: An Investigation of Image Segmentation networks on Natural Dataset

引用

IEEE ACCESS 2023年 11卷 47040-47052页

作者： Variyar, V. V. Sajith Sowmya, V. Sivanpillai, Ramesh Brown, Gregory K. Amrita Vishwa Vidyapeetham Ctr Computat Engn & Networking CEN Coimbatore 641112 India Univ Wyoming Wyoming GIS Ctr Sch Comp Laramie WY 82071 USA Univ Wyoming Dept Bot Laramie WY 82071 USA

Training deep learning-based image segmentation networks require large number of samples of adequate quality. However, obtaining large number of samples is not possible in certain domains. Recent approaches use augmentation and transfer learning techniques to overcome small sample size. Augmentation techniques are known to introduce noise to the dataset, while transfer learning approaches may fail if the existing dataset is novel to deep learning algorithms. This study investigated how four deep learning-based image segmentation networks learned and adapted to identify epiphytes when trained with fewer image samples (n = 132) of heterogeneous quality without transfer learning and data augmentation. encoder-decoder with skip connection (Unet), Deep Residual (DRUnet), Vision transformer (TransUnet), and Conditional Generative (Pix2Pix) represent different generations of deep learning networks. The segmentation performance of the trained models was evaluated by computing the Jaccard score (IoU) for predicted labels for test images. Test images (n = 20) with heterogeneous quality were evaluated by categorizing them into six categories based on target occupancy and lighting conditions. Results from this study showed that among the four networks, predicted images from the TransUnet model achieved high average Jaccard score of 0.78. Role of additional layers apart from Unet was important for accurate localization and context understanding of the target plants. However, these networks misclassified visually similar plants as target plant. The transformer and attention layers in TransUnet showed significant contribution towards improvement in localizing target and understanding context in images with varying quality. TransUnet can be used for segmenting target plants when fewer training samples are available. The presence of Unet based encoder-decoder in TransUnet is well contributing for deriving good features from minimum samples.

关键词： Training Image segmentation Deep learning Transformers Transfer learning Decoding Location awareness less training samples image quality INDEX TERMS encoder-decoder networks deep neural networks vision transformer

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：