检索结果-内蒙古大学图书馆

Multi-scale deep encoder-decoder network for salient object detection

NEUROCOMPUTING 2018年 316卷 95-104页

作者： Ren, Qinghua Hu, Renjie Southeast Univ Sch Elect Engn Nanjing Jiangsu Peoples R China

Deep convolutional neural networks (CNNs) have recently made revolutionary improvements in salient object detection. However, most existing CNN-based models fail to precisely separate the whole salient object(s) from a cluttered background due to the downsampling effects or the patch-level operation. In this paper, we propose a multi-scale deep encoder-decoder network which learns discriminative saliency cues and computes confidence scores in an end-to-end fashion. The encoder network extracts meaningful and informative features in a global view, and the decoder network recovers lost detailed object structure in a local perspective. By taking multiple resized images as the inputs, the proposed model incorporates multi-scale features from a shared network and predicts a fine-grained saliency map at the pixel level. To easily and efficiently train the whole network, the light-weighted decoder breaks through the limit of conventional symmetric structure. In addition, a two-stage training strategy is designed to encourage the robustness and accuracy of the network. Without any post-processing steps, our method is capable of significantly reducing the computation complexity while densely segmenting foreground objects from an image. Extensive experiments on six challenging datasets demonstrate that the proposed model outperforms other state-of-the-art approaches in terms of various evaluation metrics. (C) 2018 Elsevier B.V. All rights reserved.

关键词： Salient object detection Multi-scale encoder-decoder CNN

来源：评论

学校读者我要写书评

暂无评论

Cardiac-DeepIED: Automatic Pixel-Level Deep Segmentation for Cardiac Bi-Ventricle Using Improved End-to-End encoder-decoder Network

引用

IEEE JOURNAL OF TRANSLATIONAL ENGINEERING IN HEALTH AND MEDICINE 2019年 7卷 1900110-1900110页

作者： Du, Xiuquan Yin, Susu Tang, Renjun Zhang, Yanping Li, Shuo Anhui Univ Sch Comp Sci & Technol Hefei 230039 Anhui Peoples R China Western Univ Dept Med Imaging London ON N6A 3K7 Canada Digital Imaging Grp London London ON N6A 3K7 Canada

Accurate segmentation of cardiac bi-ventricle (CBV) from magnetic resonance (MR) images has a great significance to analyze and evaluate the function of the cardiovascular system. However, the complex structure of CBV image makes fully automatic segmentation as a well-known challenge. In this paper, we propose an improved end-to-end encoder-decoder network for CBV segmentation from the pixel level view (Cardiac-DeepIED). In our framework, we explicitly solve the high variability of complex cardiac structures through an improved encoder-decoder architecture which consists of Fire dilated modules and D-Fire dilated modules. This improved encoder-decoder architecture has the advantages of being capable of obtaining semantic task-aware representation and preserving fine-grained information. In addition, our method can dynamically capture potential spatiotemporal correlations between consecutive cardiac MR images through specially designed convolutional long-term and short-term memory structure;it can simulate spatiotemporal contexts between consecutive frame images. The combination of these modules enables the entire network to get an accurate, robust segmentation result. The proposed method is evaluated on the 145 clinical subjects with leave-one-out cross-validation. The average dice metric (DM) is up to 0.96 (left ventricle), 0.89 (myocardium), and 0.903 (right ventricle). The performance of our method outperforms state-of-the-art methods. These results demonstrate the effectiveness and advantages of our method for CBV regions segmentation at the pixel-level. It also reveals the proposed automated segmentation system can be embedded into the clinical environment to accelerate the quantification of CBV and expanded to volume analysis, regional wall thickness analysis, and three LV dimensions analysis.

关键词： CBV segmentation deep learning encoder-decoder magnetic resonance images

来源：评论

学校读者我要写书评

暂无评论

Automatic Building Extraction on High-Resolution Remote Sensing Imagery Using Deep Convolutional encoder-decoder With Spatial Pyramid Pooling

引用

IEEE ACCESS 2019年 7卷 128774-128786页

作者： Liu, Yaohui Gross, Lutz Li, Zhiqiang Li, Xiaoli Fan, Xiwei Qi, Wenhua China Earthquake Adm Inst Geol Beijing 100029 Peoples R China Univ Queensland Sch Earth & Environm Sci Brisbane Qld 4072 Australia China Earthquake Networks Ctr Beijing 100045 Peoples R China

Automatic extraction of buildings from remote sensing imagery plays a significant role in many applications, such as urban planning and monitoring changes to land cover. Various building segmentation methods have been proposed for visible remote sensing images, especially state-of-the-art methods based on convolutional neural networks (CNNs). However, high-accuracy building segmentation from high-resolution remote sensing imagery is still a challenging task due to the potentially complex texture of buildings in general and image background. Repeated pooling and striding operations used in CNNs reduce feature resolution causing a loss of detailed information. To address this issue, we propose a light-weight deep learning model integrating spatial pyramid pooling with an encoder-decoder structure. The proposed model takes advantage of a spatial pyramid pooling module to capture and aggregate multi-scale contextual information and of the ability of encoder-decoder networks to restore losses of information. The proposed model is evaluated on two publicly available datasets;the Massachusetts roads and buildings dataset and the INRIA Aerial Image Labeling Dataset. The experimental results on these datasets show qualitative and quantitative improvement against established image segmentation models, including SegNet, FCN, U-Net, Tiramisu, and FRRN. For instance, compared to the standard U-Net, the overall accuracy gain is 1.0% (0.913 vs. 0.904) and 3.6% (0.909 vs. 0.877) with a maximal increase of 3.6% in model-training time on these two datasets. These results demonstrate that the proposed model has the potential to deliver automatic building segmentation from high-resolution remote sensing images at an accuracy that makes it a useful tool for practical application scenarios.

关键词： Deep learning high-resolution remote sensing imagery building extraction fully convolutional networks encoder-decoder

来源：评论

学校读者我要写书评

暂无评论

Semiautomated seismic horizon interpretation using the encoder-decoder convolutional neural network

引用

GEOPHYSICS 2019年第6期84卷 B403-B417页

作者： Wu, Hao Zhang, Bo Lin, Tengfei Cao, Danping Lou, Yihuai Univ Alabama Dept Geol Sci Tuscaloosa AL 35487 USA CNPC Res Inst Petr Explorat & Dev Dept Middle East E&P Beijing Peoples R China China Univ Petr East China Sch Geosci Qingdao Shandong Peoples R China

The seismic horizon is a critical input for the structure and stratigraphy modeling of reservoirs. It is extremely hard to automatically obtain an accurate horizon interpretation for seismic data in which the lateral continuity of reflections is interrupted by faults and unconformities. The process of seismic horizon interpretation can be viewed as segmenting the seismic traces into different parts and each part is a unique object. Thus, we have considered the horizon interpretation as an object detection problem. We use the encoder-decoder convolutional neural network (CNN) to detect the "objects" contained in the seismic traces. The boundary of the objects is regarded as the horizons. The training data are the seismic traces located on a user-defined coarse grid. We give a unique training label to the time window of seismic traces bounded by two manually picked horizons. To efficiently learn the waveform pattern that is bounded by two adjacent horizons, we use variable sizes for the convolution filters, which is different than current CNN-based image segmentation methods. Two field data examples demonstrate that our method is capable of producing accurate horizons across the fault surface and near the unconformity which is beyond the current capability of horizon picking method.

关键词： seismic horizon interpretation encoder-decoder neural network

来源：评论

学校读者我要写书评

暂无评论

Image Denoising Using a Deep encoder-decoder Network with Skip Connections 25th

Image Denoising Using a Deep Encoder-Decoder Network with Sk...

引用

25th International Conference on Neural Information Processing (ICONIP)

作者： Couturier, Raphael Perrot, Gilles Salomon, Michel Univ Bourgogne Franche Comte UBFC FEMTO ST Inst CNRS Belfort France

ISBN: (纸本)9783030042240;9783030042233

In many areas images can be corrupted by various types of noise and therefore image denoising is a prerequisite. For example, medical images like the 4D-CT or ultrasound ones, are prone to noise and artifacts that can affect diagnostic confidence. Remote sensing is another field for which image preprocessing is mandatory to improve the quality of source images. Synthetic Aperture Radar (SAR) images are typically corrupted by multiplicative speckle noise. In this paper, a deep neural network able to deal with both additive white Gaussian and multiplicative speckle noises is developed, showing also some blind denoising capacity. The experiments on noisy images show that the proposal, which consists in a encoder-decoder, is efficient and competitive in comparison with state-of-the-art methods.

关键词： Image denoising Additive and multiplicative noises Deep learning encoder-decoder

来源：评论

学校读者我要写书评

暂无评论

DEEP PATCH-BASED PRIORS UNDER A FULLY CONVOLUTIONAL encoder-decoder ARCHITECTURE FOR INTERSTITIAL LUNG DISEASE SEGMENTATION 15

DEEP PATCH-BASED PRIORS UNDER A FULLY CONVOLUTIONAL ENCODER-...

引用

15th IEEE International Symposium on Biomedical Imaging (ISBI)

作者： Vakalopoulou, M. Chassagnon, G. Paragios, N. Revel, M. -P. Zacharaki, E. I. Univ Paris Saclay Cent Supelec CVN Paris France TheraPanacea Paris France Univ Patras Dept Comp Engn & Informat Patras Greece Univ Paris 05 Grp Hosp Cochin Dept Radiol Hotel Dieu Paris France

ISBN: (纸本)9781538636367

Interstitial lung diseases (ILD) encompass a large spectrum of diseases sharing similarities in their physiopathology and computed tomography (CT) appearance. In this paper, we propose the adaption of a deep convolutional encoder-decoder (CED) that has shown high accuracy for image segmentation. Such architectures require annotation of the total region with pathological findings. This is difficult to acquire, due to uncertainty in the definition and extent of disease patterns and the need of significant human effort, especially for large datasets. Therefore, often current methods use patch-based implementations of convolutional neural networks, which however tend to produce spatially inhomogeneous segmentations due to their local contextual view. We exploit the advantages of both architectures by using the output of a patch-based classifier as a prior to a CED. Our method could advance the state-of-the-art in lung tissue segmentation using only a small number of newly annotated images.

关键词： encoder-decoder probabilistic priors pixelwise classification

来源：评论

学校读者我要写书评

暂无评论

Segmental encoder-decoder Models for Large Vocabulary Automatic Speech Recognition 19

Segmental Encoder-Decoder Models for Large Vocabulary Automa...

引用

19th Annual Conference of the International-Speech-Communication-Association (INTERSPEECH 2018)

作者： Beck, Eugen Hannemann, Mirko Doetsch, Patrick Schlueter, Ralf Ney, Hermann Rhein Westfal TH Aachen Comp Sci Dept Human Language Technol & Pattern Recognit D-52062 Aachen Germany

ISBN: (纸本)9781510872219

It has been known for a long time that the classic Hidden-Markov-Model (HMM) derivation for speech recognition contains assumptions such as independence of observation vectors and weak duration modeling that are practical but unrealistic. When using the hybrid approach this is amplified by trying to fit a discriminative model into a generative one. Hidden Conditional Random Fields (CRFs) and segmental models (e.g. Semi-Markov CRFs / Segmental CRFs) have been proposed as an alternative, but for a long time have failed to get traction until recently. In this paper we explore different length modeling approaches for segmental models, their relation to attention-based systems. Furthermore we show experimental results on a handwriting recognition task and to the best of our knowledge the first reported results on the Switchboard 300h speech recognition corpus using this approach.

关键词： automatic speech recognition (ASR) (hidden) conditional random fields segmental models encoder-decoder attention mechanism

来源：评论

学校读者我要写书评

暂无评论

encoder-decoder recurrent network model for interactive character animation generation

引用

VISUAL COMPUTER 2017年第6-8期33卷 971-980页

作者： Wang, Yumeng Che, Wujun Xu, Bo Chinese Acad Sci Inst Automat Beijing Peoples R China Univ Chinese Acad Sci Beijing Peoples R China

In this paper, we propose a generative recurrent model for human-character interaction. Our model is an encoder-recurrent-decoder network. The recurrent network is composed by multiple layers of long short-term memory (LSTM) and is incorporated with an encoder network and a decoder network before and after the recurrent network. With the proposed model, the virtual character's animation is generated on the fly while it interacts with the human player. The coming animation of the character is automatically generated based on the history motion data of both itself and its opponent. We evaluated our model based on both public motion capture databases and our own recorded motion data. Experimental results demonstrate that the LSTM layers can help the character learn a long history of human dynamics to animate itself. In addition, the encoder-decoder networks can significantly improve the stability of the generated animation. This method can automatically animate a virtual character responding to a human player.

关键词： Human-character interaction Long short-term memory encoder-decoder Character animation Recurrent neural network Motion capture data

来源：评论

学校读者我要写书评

暂无评论

Multi-step-ahead Host Load Prediction with GRU Based encoder-decoder in Cloud Computing 10

Multi-step-ahead Host Load Prediction with GRU Based Encoder...

引用

10th International Conference on Knowledge and Smart Technology (KST) - Cybernetics in the Next Decades

作者： Peng, Chenglei Li, Yang Yu, Yao Zhou, Yu Du, Sidan Nanjing Univ Sch Elect Sci & Engn Nanjing Jiangsu Peoples R China

ISBN: (纸本)9781538640159

The details of the host workloads in cloud computing environment and the application demands of the real world computing system are becoming so complex that it throws a big challenge to the major cloud infrastructure vendors. To achieve service level agreements between users and cloud service vendors, it is essential to apply accurate prediction of future host load, which is also significant to improve the resource allocation and utilization in cloud computing. Although that there were several various methods and models developed, few of them can acquire the long-term temporal dependencies appropriately to make accurate predictions. In this paper, we apply a GRU based encoder-decoder network(GRUED) which contains two gated recurrent neural networks(GRUs) to address these issues. Thorough empirical studies based upon the Google resources usage traces and the traditional Unix system load traces demonstrate that our proposed method outperforms other state-of-the-art approaches for the prediction of multi-step-ahead host workload in cloud computing.

关键词： Cloud computing encoder-decoder Recurrent neural network Host load prediction GRU

来源：评论

学校读者我要写书评

暂无评论

A COMPARISON OF TECHNIQUES FOR LANGUAGE MODEL INTEGRATION IN encoder-decoder SPEECH RECOGNITION

A COMPARISON OF TECHNIQUES FOR LANGUAGE MODEL INTEGRATION IN...

引用

IEEE Workshop on Spoken Language Technology (SLT)

作者： Toshniwal, Shubham Kannan, Anjuli Chiu, Chung-Cheng Wu, Yonghui Sainath, Tara N. Livescu, Karen Toyota Technol Inst Chicago IL 60637 USA Google Inc Mountain View CA USA

ISBN: (纸本)9781538643341

Attention-based recurrent neural encoder-decoder models present an elegant solution to the automatic speech recognition problem. This approach folds the acoustic model, pronunciation model, and language model into a single network and requires only a parallel corpus of speech and text for training. However, unlike in conventional approaches that combine separate acoustic and language models, it is not clear how to use additional (unpaired) text. While there has been previous work on methods addressing this problem, a thorough comparison among methods is still lacking. In this paper, we compare a suite of past methods and some of our own proposed methods for using unpaired text data to improve encoder-decoder models. For evaluation, we use the medium-sized Switchboard data set and the large-scale Google voice search and dictation data sets. Our results confirm the benefits of using unpaired text across a range of methods and data sets. Surprisingly, for first-pass decoding, the rather simple approach of shallow fusion performs best across data sets. However, for Google data sets we find that cold fusion has a lower oracle error rate and outperforms other approaches after second-pass rescoring on the Google voice search data set.

关键词： speech recognition encoder-decoder language model shallow fusion cold fusion deep fusion

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：