检索结果-内蒙古大学图书馆

Interspeech Conference

作者： Han, Chang Xu, Xinmeng Tu, Weiping Yang, Yuhong Liu, Yajie Wuhan Univ Sch Comp Sci NERCMS Wuhan Peoples R China Hubei Luojia Lab Wuhan Peoples R China Wuhan Univ Hubei Key Lab Multimedia & Network Commun Engn Wuhan Peoples R China

Acoustic echo cancellation (AEC) aims to remove interference signals while leaving near-end speech least distorted. As the indistinguishable patterns between near-end speech and interference signals, near-end speech can't be separated completely, causing speech distortion and interference signals residual. We observe that besides target positive information, e.g., ground-truth speech and features, the target negative information, such as interference signals and features, helps make pattern of target speech and interference signals more discriminative. Therefore, we present a novel AEC model encoder-decoder architecture with the guidance of negative information termed as CMNet. A collaboration module (CM) is designed to establish the correlation between the target positive and negative information in a learnable manner via three blocks: target positive, target negative, and interactive block. Experimental results demonstrate our CMNet achieves superior performance than recent methods.

关键词： acoustic echo cancellation encoder-decoder architecture target positive and negative information

来源：评论

学校读者我要写书评

暂无评论

OverSegNet: A convolutional encoder-decoder network for image over-segmentation

引用

COMPUTERS & ELECTRICAL ENGINEERING 2023年第1期107卷

作者： Li, Peng Ma, Wei Beijing Univ Technol Fac Informat Technol Beijing 100124 Peoples R China

Efficient and differentiable image over-segmentation is key to superpixel-based research and applications but remains a challenging problem. The paper proposes a fully convolutional deep network, named OverSegNet, for image over-segmentation. OverSegNet consists of an encoder and a decoder, which are designed for the two core parts of over-segmentation, i.e., feature representation and pixel-superpixel association, respectively. To obtain edge -sensitive and noise-insusceptible feature representation, the encoder is endowed with rich over-segmentation-specific convolutional kernels via over-parametrization followed by task -driven neural network search (NAS). The decoder adopts a multi-scale convolutional structure with cross-large-scale connections, to achieve pixel-superpixel association in a coarse-to-fine feed-forward manner while eliminating accumulation errors. We conduct rich ablation studies to verify the effectiveness of the specially designed encoder and decoder. Experiments on both the BSDS500 dataset and NYUv2 dataset show that the proposed OverSegNet is fast, obtains state-of-the-art accuracy and has good generalization ability. Using semantic segmentation and disparity estimation as examples, we also verify the proposed OverSegNet in downstream applications.

关键词： Image over-segmentation Superpixel segmentation encoder-decoder architecture NAS encoder Non-iterative deep clustering

来源：评论

学校读者我要写书评

暂无评论

Intelligent Spectrum Sensing with ConvNet for 5G and LTE Signals Identification 22

Intelligent Spectrum Sensing with ConvNet for 5G and LTE Sig...

引用

22nd IEEE Statistical Signal Processing Workshop (SSP)

作者： Thien Huynh-The Quoc-Viet Pham Thai-Hoc Vu da Costa, Daniel Benevides Van-Phuc Hoang HCMC Univ Technol & Educ Dept Comp & Commun Engn Ho Chi Minh City Vietnam Trinity Coll Dublin Sch Comp Sci & Stat Dublin Ireland Univ Ulsan Dept Elect Elect & Comp Engn Ulsan South Korea Technol Innovat Inst Abu Dhabi U Arab Emirates Le Quy Don Tech Univ Inst Syst Integrat Hanoi Vietnam

ISBN: (纸本)9781665452458

The paper presents an intelligent spectrum sensing approach for next-generation wireless networks by exploiting deep learning, in which we develop a deep convolutional network (ConvNet) to automatically identify Fifth Generation New Radio (5G NR) and Long-Term Evolution (LTE) signals under standards-specified channel models with diversified RF impairments. In particular, we design a semantic segmentation ConvNet to detect and localize the spectral content of 5G NR and LTE in a synthetic signal featured by spectrum occupancy. A received signal is first converted by a short-time Fourier transform and represented as a wideband spectrogram image which is then passed through the ConvNet, incorporated by DeepLabv3+ and ResNet18 to improve the accuracy of pixel-wise segmentation to further increase the accuracy of signal identification. In the simulations, our ConvNet achieves around 95% mean accuracy and 91% mean intersection-over-union (IoU) at medium SNR level and demonstrates robustness under various practical channel impairments.

关键词： 5G NR cognitive ration deep learning encoder-decoder architecture signal identification spectrum sensing

来源：评论

学校读者我要写书评

暂无评论

SEMANTIC SEGMENTATION OF UAV IMAGES BASED ON U-NET IN URBAN AREA 6

SEMANTIC SEGMENTATION OF UAV IMAGES BASED ON U-NET IN URBAN ...

引用

ISPRS GeoSpatial Conference / Joint 6th Sensors and Models in Photogrammetry and Remote Sensing Conference (SMPR) / 4th Geospatial Information Research (GIResearch) Conference

作者： Majidizadeh, A. Hasani, H. Jafari, M. Tafresh Univ Dept Geodesy & Surveying Engn Tafresh Iran

Semantic segmentation of aerial data has been one of the leading researches in the field of photogrammetry, remote sensing, and computer vision in recent years. Many applications, including airborne mapping of urban scenes, object positioning in aerial images, automatic extraction of buildings from remote sensing or high-resolution aerial images, etc., require accurate and efficient segmentation algorithms. According to the high potential of deep learning algorithms in the classification of complex scenes, this paper aims to train a deep learning model to evaluate the semantic segmentation accuracy of UAV-based images in urban areas. The proposed method implements a deep learning framework based on the U-Net encoder-decoder architecture, which extracts and classifies features through layers of convolution, max pooling, activation, and concatenation in an end-to-end process. The obtained results compare with two traditional machine learning models, Random Forest (RF) and Multi-Layer Perceptron (MLP). They rely on two steps that involve extracting features and classifying images. In this study, the experiments are performed on the UAVid2020 semantic segmentation dataset from the ISPRS database. Results show the effectiveness of the proposed deep learning framework, so that the U-Net architecture achieved the best results with 75.15% overall accuracy, compared to RF and MLP algorithms with 52.51% and 54.65% overall accuracy, respectively.

关键词： Semantic Segmentation UAV Deep Learning Convolutional Neural Network encoder-decoder architecture UNet

来源：评论

学校读者我要写书评

暂无评论

A contrastive triplet network for automatic chest X-ray reporting

引用

NEUROCOMPUTING 2022年 502卷 71-83页

作者： Yang, Yan Yu, Jun Jiang, Hanliang Han, Weidong Zhang, Jian Jiang, Wei Hangzhou Dianzi Univ Sch Comp Sci & Technol Key Lab Complex Syst Modeling & Simulat Hangzhou 310018 Peoples R China Zhejiang Univ Coll Med Reg Med Ctr Natl Inst Resp DisSir Run Run Shaw Hosp Hangzhou 310016 Peoples R China Zhejiang Univ Sir Run Run Shaw Hosp Coll Med Dept Med Oncol Hangzhou 310016 Peoples R China Zhejiang Int Studies Univ Sch Sci & Technol Hangzhou 310023 Peoples R China

Chest X-ray reporting aims at generating linguistic descriptions automatically for chest X-ray images, in which accurate detection and description of abnormalities are essential. However, the seriously biased data distribution (e.g., the normal cases usually dominate the whole dataset over abnormal cases) causes huge challenges for the data-driven neural models to generate satisfied abnormality descriptions. To this end, we propose a contrastive triplet network (CTN) built on the Transformer architecture for automatic chest X-ray reporting to alleviate the data-bias problem. Our CTN effectively enhances abnormalities by comparing visual and semantic information between normal and abnormal cases using a triplet network. Specifically, triplets including normal and abnormal cases are first constructed. Then, visual tokens of the chest X-ray are extracted and fed to the Transformer to generate an associated report. During training, comparisons between normal and abnormal cases are conducted via contrasting: 1) the visual embedding of the chest X-ray image encoded by the Transformer encoder, and 2) the semantic embedding of the generated report encoded by a pre-trained textual encoder. Comprehensive experiments on two publicly-available databases have shown the good performance of our method. (C) 2022 Published by Elsevier B.V.

关键词： Chest X-ray report generation Data bias Triplet network Contrastive learning Transformer Textual encoder encoder-decoder architecture

来源：评论

学校读者我要写书评

暂无评论

A hybrid lightweight encoder-decoder network for automatic bridge crack assessment with real-world interference

引用

MEASUREMENT 2023年第1期216卷

作者： Deng, Jianghua Lu, Ye Lee, Vincent C. S. Changzhou Inst Technol Sch Civil Engn & Architecture Dept Struct Engn Changzhou 213032 Jiangsu Peoples R China Monash Univ Dept Civil Engn Melbourne Australia Monash Univ Fac Informat Technol Melbourne Australia

Although many learning-based studies have been conducted to detect cracks, there are still many problems in practice, such as slow inference speed due to a large number of hyperparameters required in network archiotectures and compromised detection accuracy in different environments. To address these issues, the current study employed a Hybrid Lightweight encoder-decoder Network (HLEDNet) as an ad-hoc crack segmentation and measurement system on real-world images captured from various concrete bridges. The proposed HLEDNet model was trained and tested with 3000 annotated images with further extensive data augmentation, which achieved 86.92%, 85.71%, 86.31, and 86.01% in precision, recall, F1 score, and mean intersection over union (mIoU), respectively. A crack measurement module was proposed using combined postprocessing techniques, where the R-squared values of the regression lines in crack length and average crack width are 0.9857 and 0.9925, respectively. Finally, an experimental study was undertaken to convert the crack measuring unit from pixel to millimetre.

关键词： Structural health monitoring Concrete bridge cracks Atrous convolutions encoder-decoder architecture Crack measurement Automated inspection

来源：评论

学校读者我要写书评

暂无评论

Two-stage deep image restoration network with application to single image shadow removal

引用

APPLIED SOFT COMPUTING 2024年 167卷

作者： Yeh, Chia-Hung Zhan, Zhi-Xiang Kang, Li-Wei Natl Taiwan Normal Univ Dept Elect Engn Taipei Taiwan Natl Sun Yat Sen Univ Dept Elect Engn Kaohsiung Taiwan

In this paper, we introduce a two-stage deep learning-based image restoration network and its application to remove shadow information from a single image, named by ESCNet (encoder-decoder based Shadow removal with Colorization Network). Most existed single image-based shadow removal methods may suffer from that the shadow contains multiple regions of different colors or rich image details. To tackle with the problems, our key idea is to first remove shadow(s) from an image followed by repainting the shadow-removed region(s) in this image. To accomplish this, we present a deep two-stage network, cascading a shadow removal network (SRN) and a colorization network (CN). The presented encoder-decoder-based SRN with fusion of global and local feature information is used to remove the shadow(s) in the grayscale domain of the input image while recovering the image details for the shadow-removed region(s). Then the proposed CN aims at repainting the removed shadow region(s) via re-colorization. The proposed deep model has been well trained and well evaluated on the two well-known public datasets, i.e., ISTD (Image Shadow Triplets Dataset) and SRD (Shadow Removal Dataset). Experimental results have shown that the proposed method outperforms the compared state-of-the-art (SOTA) shadow removal approaches quantitatively and qualitatively.

关键词： Convolutional neural networks Shadow removal encoder-decoder architecture Colorization Deep learning

来源：评论

学校读者我要写书评

暂无评论

HCS-Net: Multi-level deformation strategy combined with quadruple attention for image registration

引用

COMPUTERS IN BIOLOGY AND MEDICINE 2024年 168卷 107832-107832页

作者： Ou, Zhuolin Lu, Xiaoqi Gu, Yu Inner Mongolia Univ Sci & Technol Sch Informat Engn Inner Mongolia Key Lab Pattern Recognit & Intellig Baotou 014010 Peoples R China Inner Mongolia Univ Technol Sch Informat Engn Hohhot 010051 Peoples R China

Background and objective: Non-rigid image registration plays a significant role in computer-aided diagnosis and surgical navigation for brain diseases. Registration methods that utilize convolutional neural networks (CNNs) have shown excellent accuracy when applied to brain magnetic resonance images (MRI). However, CNNs have limitations in understanding long-range spatial relationships in images, which makes it challenging to incorporate contextual information. And in intricate image registration tasks, it is difficult to achieve a satisfactory dense prediction field, resulting in poor registration ***: This paper proposes a multi-level deformable unsupervised registration model that combines Trans-former and CNN to achieve non-rigid registration of brain MRI. Firstly, utilizing a dual encoder structure to establish the dependency relationship between the global features of two images and to merge features of varying scales, as well as to preserve the relative spatial position information of feature maps at different scales. Then the proposed multi-level deformation strategy utilizes different deformable fields of varying resolutions generated by the decoding structure to progressively deform the moving image. Ultimately, the proposed quadruple attention module is incorporated into the decoding structure to merge feature information from various directions and emphasize the spatial features in the dominant ***: The experimental results on multiple brain MR datasets demonstrate that the promising network could provide accurate registration and is comparable to state-of-the-art ***: The proposed registration model can generate superior deformable fields and achieve more precise registration effects, enhancing the auxiliary role of medical image registration in various fields and advancing the development of computer-aided diagnosis, surgical navigation, and related domains.

关键词： Transformer model encoder-decoder architecture Medical images Non-rigid registration Feature fusion

来源：评论

学校读者我要写书评

暂无评论

S3L: Spectrum Transformer for Self-Supervised Learning in Hyperspectral Image Classification

引用

REMOTE SENSING 2024年第6期16卷 970页

作者： Guo, Hufeng Liu, Wenyi North Univ China Sch Instrument & Elect State Key Lab Dynam Measurement Technol Taiyuan 030051 Peoples R China Henan Coll Transportat Dept Transportat Informat Engn Zhengzhou 451460 Peoples R China

In the realm of Earth observation and remote sensing data analysis, the advancement of hyperspectral imaging (HSI) classification technology is of paramount importance. Nevertheless, the intricate nature of hyperspectral data, coupled with the scarcity of labeled data, presents significant challenges in this domain. To mitigate these issues, we introduce a self-supervised learning algorithm predicated on a spectral transformer for HSI classification under conditions of limited labeled data, with the objective of enhancing the efficacy of HSI classification. The S3L algorithm operates in two distinct phases: pretraining and fine-tuning. During the pretraining phase, the algorithm learns the spatial representation of HSI from unlabeled data, utilizing a masking mechanism and a spectral transformer, thereby augmenting the sequence dependence of spectral features. Subsequently, in the fine-tuning phase, labeled data is employed to refine the pretrained weights, thereby improving the precision of HSI classification. Within the comprehensive encoder-decoder framework, we propose a novel spectral transformer module specifically engineered to synergize spatial feature extraction with spectral domain analysis. This innovative module adeptly navigates the complex interplay among various spectral bands, capturing both global and sequential spectral dependencies. Uniquely, it incorporates a gated recurrent unit (GRU) layer within the encoder to enhance its ability to process spectral sequences. Our experimental evaluations across several public datasets reveal that our proposed method, distinguished by its spectral transformer, achieves superior classification performance, particularly in scenarios with limited labeled samples, outperforming existing state-of-the-art approaches.

关键词： hyperspectral image classification self-supervised learning spectral transformer encoder-decoder architecture limited labeled data

来源：评论

学校读者我要写书评

暂无评论

Are Graphs and GCNs necessary for short-term metro ridership forecasting?

引用

EXPERT SYSTEMS WITH APPLICATIONS 2024年 254卷

作者： Yang, Qiong Xu, Xianghua Wang, Zihang Yu, Juan Hu, Xiaodong Hangzhou Dianzi Univ Sch Comp Sci Hangzhou 310018 Peoples R China Zhejiang Ind Polytech Coll Dept Art & Design Shaoxing 312000 Peoples R China Zhejiang Normal Univ Sch Comp Sci & Technol Jinhua 321004 Peoples R China

Short-term metro ridership prediction is of great significance to efficient and economic operation of Urban Rail Transit (URT) systems. With the popularity of Graph Convolution Networks (GCN) and Transformers, the recent notable metro ridership forecasting methods are GCN-based and Transformer -based models. However, existing methods face the following drawbacks. First, GCN-based models fail to effectively capture global spatial correlations which are significant for accurate prediction. Second, Transformer -based models are prone to loss temporal information due to the permutation -invariant and anti -order properties of the self -attention which they used for capturing temporal correlations. To overcome the drawbacks, we propose a novel sequence -tosequence metro ridership prediction model, named SDT-GRU, with Stacked DT-GRU layers as both encoder and decoder. The core component of our model is DT-GRU, which integrates Dual -branch Transformer decoder into the GRU to effectively capture global spatial correlations and temporal correlations with Transformer decoder and GRU, separately. In particular, the DT-GRU module uses one branch Transformer encoder layer to capture spatial correlations within the same timestamp, and adopts another Transformer encoder layer to implicitly capture spatio-temporal correlations among previous timestamps. Then, outputs of the two Transformer encoder layers are fed into a GRU layer to capturing spatio-temporal patterns. To evaluate the effectiveness of the proposed SDT-GRU, we conduct comprehensive experiments on three real -world metro ridership datasets from Beijing, Shanghai and Hangzhou. Experimental results demonstrate that our SDT-GRU achieves better prediction performance than the state-of-the-art baselines.

关键词： Metro ridership prediction Transformer encoder GRU encoder-decoder architecture Graph convolutional networks (GCNs)

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：