检索结果-内蒙古大学图书馆

Interspeech Conference

作者： Xu, Xinmeng Wang, Yang Jia, Jie Chen, Binbin Hao, Jianjun Trinity Coll Dublin Elect & Elect Engn Dublin Ireland Vivo AI Lab Shenzhen Peoples R China Hubei Univ Chinese Med Sch Foreign Languages Wuhan Peoples R China

For monaural speech enhancement, contextual information is important for accurate speech estimation. However, commonly used convolution neural networks (CNNs) are weak in capturing temporal contexts since they only build blocks that process one local neighborhood at a time. To address this problem, we learn from human auditory perception to introduce a two-stage trainable reasoning mechanism, referred as global-local dependency (GLD) block. GLD blocks capture long-term dependency of time-frequency bins both in global level and local level from the noisy spectrogram to help detecting correlations among speech part, noise part, and whole noisy input. What is more, we conduct a monaural speech enhancement network called GLD-Net, which adopts encoder-decoder architecture and consists of speech object branch, interference branch, and global noisy branch. The extracted speech feature at global-level and local-level are efficiently reasoned and aggregated in each of the branches. We compare the proposed GLD-Net with existing state-of-art methods on WSJ0 and DEMAND dataset. The results show that GLD-Net outperforms the state-of-the-art methods in terms of PESQ and STOI.

关键词： monaural speech enhancement global and local dependency encoder-decoder architecture two-stage trainable reasoning mechanism

来源：评论

学校读者我要写书评

暂无评论

ABSTRACTIVE HEADLINE GENERATION FOR SPOKEN CONTENT BY ATTENTIVE RECURRENT NEURAL NETWORKS WITH ASR ERROR MODELING

ABSTRACTIVE HEADLINE GENERATION FOR SPOKEN CONTENT BY ATTENT...

引用

IEEE Workshop on Spoken Language Technology (SLT)

作者： Yu, Lang-Chi Lee, Hung-yi Lee, Lin-shan Natl Taiwan Univ Grad Inst Commun Engn Taipei Taiwan Natl Taiwan Univ Grad Inst Comp Sci & Informat Engn Taipei Taiwan

ISBN: (纸本)9781509049035

Headline generation for spoken content is important since spoken content is difficult to be shown on the screen and browsed by the user. It is a special type of abstractive summarization, for which the summaries are generated word by word from scratch without using any part of the original content. Many deep learning approaches for headline generation from text document have been proposed recently, all requiring huge quantities of training data, which is difficult for spoken document summarization. In this paper, we propose an ASR error modeling approach to learn the underlying structure of ASR error patterns and incorporate this model in an Attentive Recurrent Neural Network (ARNN) architecture. In this way, the model for abstractive headline generation for spoken content can be learned from abundant text data and the ASR data for some recognizers. Experiments showed very encouraging results and verified that the proposed ASR error model works well even when the input spoken content is recognized by a recognizer very different from the one the model learned from.

关键词： abstractive summarization headline generation ASR error modeling attention mechanism encoder-decoder architecture

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

CLR2G: Cross-modal Contrastive Learning on Radiology Report Generation 24

CLR2G: Cross-modal Contrastive Learning on Radiology Report ...

引用

33rd ACM International Conference on Information and Knowledge Management (CIKM)

作者： Xue, Hongchen Ma, Qingzhi Liu, Guanfeng Qu, Jianfeng Liu, Yuanjun Liu, An Soochow Univ Sch Comp Sci & Technol Suzhou Peoples R China Macquarie Univ Sch Comp Sydney NSW Australia

ISBN: (纸本)9798400704369

The automatic generation of radiological imaging reports aims to produce accurate and coherent clinical descriptions based on X-ray images. This facilitates clinicians in completing the arduous task of report writing and advances clinical automation. The primary challenge in radiological imaging report generation lies in accurately capturing and describing abnormal regions in the images under data bias conditions, resulting in the generation of lengthy texts containing image details. Existing methods mostly rely on prior knowledge such as medical knowledge graphs, corpora, and image databases to assist models in generating more precise textual descriptions. However, these methods still struggle to identify rare anomalies in the images. To address this issue, we propose a two-stage training model, named CLR2G, based on cross-modal contrastive learning. This model delegates the task of capturing anomalies, particularly those challenging for the generative model trained with cross-entropy loss under data bias conditions, to a specialized abnormality capture component. Specifically, we employ a semantic matching loss function to train additional abnormal image and text encoders through cross-modal contrastive learning, facilitating the capture of 13 common anomalies. We utilize the anomalous image features, text features and their confidence probabilities as a posteriori knowledge to help the model generate accurate image reports. Experimental results demonstrate the state-of-the-art performance of our method on two widely used public datasets, IU-Xray and MIMIC-CXR.

关键词： Medical Data Mining Radiology Image Report Generation encoder-decoder architecture Contrastive Learning

来源：评论

学校读者我要写书评

暂无评论

TATL: Task agnostic transfer learning for skin attributes detection

引用

MEDICAL IMAGE ANALYSIS 2022年第0期78卷 102359-102359页

作者： Nguyen, Duy M. H. Nguyen, Thu T. Vu, Huong Pham, Quang Manh-Duy Nguyen Nguyen, Binh T. Sonntag, Daniel German Res Ctr Artificial Intelligence Saarbrucken Germany Max Planck Inst Informat Saarbrucken Germany Univ Louisiana Lafayette Lafayette LA 70504 USA Univ Calif Berkeley Berkeley CA 94720 USA Singapore Management Univ Sch Comp & Informat Syst Singapore Singapore Dublin City Univ Sch Comp Dublin Ireland AISIA Res Lab Ho Chi Minh City Vietnam Univ Science Ho Chi Minh City Vietnam Vietnam Natl Univ Ho Chi Minh City Vietnam Oldenburg Univ Oldenburg Germany

Existing skin attributes detection methods usually initialize with a pre-trained Imagenet network and then fine-tune on a medical target task. However, we argue that such approaches are suboptimal be-cause medical datasets are largely different from ImageNet and often contain limited training samples. In this work, we propose Task Agnostic Transfer Learning (TATL), a novel framework motivated by der-matologists' behaviors in the skincare context. TATL learns an attribute-agnostic segmenter that detects lesion skin regions and then transfers this knowledge to a set of attribute-specific classifiers to detect each particular attribute. Since TATL's attribute-agnostic segmenter only detects skin attribute regions, it enjoys ample data from all attributes, allows transferring knowledge among features, and compensates for the lack of training data from rare attributes. We conduct extensive experiments to evaluate the pro-posed TATL transfer learning mechanism with various neural network architectures on two popular skin attributes detection benchmarks. The empirical results show that TATL not only works well with multi -ple architectures but also can achieve state-of-the-art performances, while enjoying minimal model and computational complexities. We also provide theoretical insights and explanations for why our transfer learning framework performs well in practice.(c) 2022 Elsevier B.V. All rights reserved.

关键词： Transfer learning Skin attribute detection encoder-decoder architecture

来源：评论

学校读者我要写书评

暂无评论

ClarifyNet: A high-pass and low-pass filtering based CNN for single image dehazing

引用

JOURNAL OF SYSTEMS architecture 2022年第0期132卷

作者： Susladkar, Onkar Deshmukh, Gayatri Nag, Subhrajit Mantravadi, Ananya Makwana, Dhruv Ravichandran, Sujitha Teja, R. Sai Chandra Chavhan, Gajanan H. Mohan, C. Krishna Mittal, Sparsh Vishwakarma Inst Informat Technol Pune India IIT Hyderabad Hyderabad India IIIT Raichur Raichur India CKM Vigil Pvt Ltd Hyderabad India NIT Trichy Trichy India IIT Roorkee Roorkee India

Dehazing refers to removing the haze and restoring the details from hazy images. In this paper, we propose ClarifyNet, a novel, end-to-end trainable, convolutional neural network architecture for single image dehazing. We note that a high-pass filter detects sharp edges, texture, and other fine details in the image, whereas a low-pass filter detects color and contrast information. Based on this observation, our key idea is to train ClarifyNet on ground-truth haze-free images, low-pass filtered images, and high-pass filtered images. Based on this observation, we present a shared-encoder multi-decoder model ClarifyNet which employs interconnected parallelization. While training, ground-truth haze-free images, low-pass filtered images, and high-pass filtered images undergo multi-stage filter fusion and attention. By utilizing a weighted loss function composed of SSIM loss and L1 loss, we extract and propagate complementary features. We comprehensively evaluate ClarifyNet on I-HAZE, O-HAZE, Dense-Haze, NH-HAZE, SOTS-Indoor, SOTS-Outdoor, HSTS, and Middlebury datasets. We use PSNR and SSIM metrics and compare the results with previous works. For most datasets, ClarifyNet provides the highest scores. On using EfficientNet-B6 as the backbone, ClarifyNet has 18 M parameters (model size of similar to 71 MB) and a throughput of 8 frames-per-second while processing images of size 2048 x 1024.

关键词： Single-image dehazing Convolutional neural network encoder-decoder architecture Attention Low-pass filter High-pass filter

来源：评论

学校读者我要写书评

暂无评论

Mixed spatial pyramid pooling for semantic segmentation

引用

APPLIED SOFT COMPUTING 2020年 91卷 106209-106209页

作者： Xia, Zhengyu Kim, Joohee IIT Dept Elect & Comp Engn Chicago IL 60616 USA

Semantic segmentation is a challenging task as each pixel should be labeled accurately in the image. To improve the performance of semantic segmentation, some Fully Convolutional Network (FCN) based semantic segmentation methods adopt a spatial pyramid pooling structure to enrich contextual information. Others employ an encoder-decoder architecture to recover object details gradually. In this paper, we propose a semantic segmentation framework which combines the benefits of these approaches. Specifically, we propose a Mixed Spatial Pyramid Pooling (MSPP) module based on region-based average pooling and dilated convolution to obtain dense multi-level contextual priors. To further refine the details of objects more effectively, we also propose a Global-Attention Fusion (GAF) module to provide global context as guidance for low-level features. Our proposed method achieves mIoU of 84.1% on PASCAL VOC 2012 dataset and 80.4% on Cityscapes dataset without using any post-processing or additional datasets for pretrained model. (C) 2020 Elsevier B.V. All rights reserved.

关键词： Semantic segmentation Convolutional neural network Spatial pyramid pooling Dilated convolution encoder-decoder architecture Scene understanding

来源：评论

学校读者我要写书评

暂无评论

Self-co-attention neural network for anatomy segmentation in whole breast ultrasound

引用

MEDICAL IMAGE ANALYSIS 2020年 64卷 101753-101753页

作者： Lei, Baiying Huang, Shan Li, Hang Li, Ran Bian, Cheng Chou, Yi-Hong Qin, Jing Zhou, Peng Gong, Xuehao Cheng, Jie-Zhi Shenzhen Univ Natl Reg Key Technol Engn Lab Med Ultrasound Guangdong Key Lab Biomed Measurements & Ultrasoun Sch Biomed EngnHlth Sci Ctr Shenzhen 518060 Peoples R China Yuanpei Univ Med Technol Dept Med Imaging & Radiol Technol Hsinchu Taiwan Natl Yang Ming Univ Taipei Vet Gen Hosp Dept Radiol Taipei Taiwan Natl Yang Ming Univ Sch Med Taipei Taiwan Yee Zen Gen Hosp Dept Radiol Taoyuan Taiwan Hong Kong Polytech Univ Sch Nursing Ctr Smart Hlth Hong Kong Peoples R China Shenzhen Univ Peoples Hosp Shenzhen 2 Affiliated Hosp 1 Dept UltrasoundShenzhen Peoples Hosp 2 Shenzhen 518035 Peoples R China Shanghai United Imaging Intelligence Co Ltd UII Shanghai Peoples R China

The automated whole breast ultrasound (AWBUS) is a new breast imaging technique that can depict the whole breast anatomy. To facilitate the reading of AWBUS images and support the breast density estimation, an automatic breast anatomy segmentation method for AWBUS images is proposed in this study. The problem at hand is quite challenging as it needs to address issues of low image quality, ill-defined boundary, large anatomical variation, etc. To address these issues, a new deep learning encoder-decoder segmentation method based on a self-co-attention mechanism is developed. The self-attention mechanism is comprised of spatial and channel attention module (SC) and embedded in the ResNeXt (i.e., Res-SC) block in the encoder path. A non-local context block (NCB) is further incorporated to augment the learning of high-level contextual cues. The decoder path of the proposed method is equipped with the weighted up-sampling block (WUB) to attain class-specific better up-sampling effect. Meanwhile, the co-attention mechanism is also developed to improve the segmentation coherence among two consecutive slices. Extensive experiments are conducted with comparison to several the state-of-the-art deep learning segmentation methods. The experimental results corroborate the effectiveness of the proposed method on the difficult breast anatomy segmentation problem on AWBUS images. (C) 2020 Elsevier B.V. All rights reserved.

关键词： Breast anatomy segmentation Self-co-attention mechanism Non-local cue encoder-decoder architecture

来源：评论

学校读者我要写书评

暂无评论

WaferSegClassNet - A light-weight network for classification and segmentation of semiconductor wafer defects

引用

COMPUTERS IN INDUSTRY 2022年 142卷

作者： Nag, Subhrajit Makwana, Dhruv Teja, Sai Chandra R. Mittal, Sparsh Mohan, C. Krishna IIT Hyderabad Hyderabad India CKMVigil Pvt Ltd Hyderabad India IIT Roorkee Roorkee Uttar Pradesh India

As the integration density and design intricacy of semiconductor wafers increase, the magnitude and complexity of defects in them are also on the rise. Since the manual inspection of wafer defects is costly, an automated artificial intelligence (AI) based computer-vision approach is highly desired. The previous works on defect analysis have several limitations, such as low accuracy and the need for separate models for classification and segmentation. For analyzing mixed-type defects, some previous works require separately training one model for each defect type, which is non-scalable. In this paper, we present WaferSegClassNet (WSCN), a novel network based on encoder-decoder architecture. WSCN performs simultaneous classification and segmentation of both single and mixed-type wafer defects. WSCN uses a "shared encoder" for classification, and segmentation, which allows training WSCN end-to-end. We use N-pair contrastive loss to first pretrain the encoder and then use BCE-Dice loss for segmentation, and categorical cross-entropy loss for classification. Use of N-pair contrastive loss helps in better embedding representation in the latent dimension of wafer maps. WSCN has a model size of only 0.51MB and performs only 0.2 M FLOPS. Thus, it is much lighter than other state-of-the-art models. Also, it requires only 150 epochs for convergence, compared to 4000 epochs needed by a previous work. We evaluate our model on the MixedWM38 dataset, which has 38,015 images. WSCN achieves an average classification accuracy of 98.2% and a dice coefficient of 0.9999. We are the first to show segmentation results on the MixedWM38 dataset. The source code can be obtained from https://***/ckmvigil/WaferSegClassNet. (C) 2022 Elsevier B.V. All rights reserved.

关键词： Image classification Image Segmentation Semiconductor wafer defect analysis Convolution neural network encoder-decoder architecture

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：