检索结果-内蒙古大学图书馆

Attention-shift based deep neural network for fine-grained visual categorization

PATTERN RECOGNITION 2021年 116卷 107947-107947页

作者： Niu, Yi Jiao, Yang Shi, Guangming Xidian Univ Sch Elect Engn 2 Taibai South Rd Xian Shaanxi Peoples R China Xidian Univ Sch Artificial Intelligence 2 Taibai South Rd Xian Shaanxi Peoples R China

Fine-grained visual categorization (FGVC) has attracted extensive attention in recent years. The general pipeline of current FGVC techniques is to 1) locate the discriminative regions;2) extract features from each region independently;and 3) feed the integrated features to a classifier. In this paper, we reinvestigate the pipeline from the view of human visual recognition mechanisms. The perceiving of discriminative regions is a temporal processing by the human visual system (HVS) via the attention-shift mechanism. However, the existing independent feature extracting and one-pass feeding strategy ignore the inherent semantic relationships among discriminative regions, and thus is improper to model the attention-shift process properly. Therefore, in this paper, we propose a novel end-to-end FGVC network structure named Attention-Shift based Deep Neural Network (AS-DNN) to locate the discriminative regions automatically and encode the semantic correlations iteratively. AS-DNN consists of two channels: 1) the global perception channel C-glb and 2) the attention-shift channel C-sft, simulating the global perception and the attention-shift mechanism, respectively. Experimental results show that AS-DNN achieves state-of-the-art performances by outperforming both the CNN-based weakly or strongly-supervised FGVC algorithms on several widely-used fine-grained datasets, and the visualization of attention regions exhibit that the proposed method can locate the discriminative regions robustly in complex backgrounds and postures. (C) 2021 Elsevier Ltd. All rights reserved.

关键词： Fine-grained visual categorization Deep neural network Human perception mechanism Attention-shift encoder-decoder

来源：评论

学校读者我要写书评

暂无评论

A Deep Sequence-to-Sequence Method for Aircraft Landing Speed Prediction Based on QAR Data 21st

A Deep Sequence-to-Sequence Method for Aircraft Landing Spee...

引用

21st International Conference on Web Information Systems Engineering (WISE)

作者： Kang, Zongwei Shang, Jiaxing Feng, Yong Zheng, Linjiang Liu, Dajiang Qiang, Baohua Wei, Ran Chongqing Univ Coll Comp Sci Chongqing Peoples R China Chongqing Univ Key Lab Dependable Serv Comp Cyber Phys Soc Minist Educ Chongqing Peoples R China Guilin Univ Elect Technol Guangxi Key Lab Optoelect Informat Proc Guilin Peoples R China Guilin Univ Elect Technol Guangxi Key Lab Trusted Software Guilin Peoples R China Chongqing Med Data Informat Technol Co Ltd Chongqing Peoples R China

ISBN: (纸本)9783030620080;9783030620073

Runway overrun is one of the most typical landing incidents highly concerned by airlines in the aviation industry. Previous studies have shown that high landing speed is closely related to runway overrun risks, therefore the study of landing speed prediction based on flight data has drawn attention of many scholars in recent years. However, existing methods are mainly based on traditional machine learning models and handcrafted features, which not only rely heavily on flight experts' priori knowledge, but also provide unsatisfactory prediction accuracy. To solve this problem, in this paper we propose an innovative deep encoder-decoder model for aircraft landing speed prediction based on Quick Access Recorder (QAR) data. Specifically, we first preprocess the QAR dataset through a data cleaning, Lagrange interpolation and normalization procedure. Second, based on the preprocessed QAR dataset, we use gradient boosting decision trees to select features which are most closely related to landing speed. Finally, we employ the LSTM encoder-decoder architecture where the encoder captures the pattern underlying in the past sequences while the decoder generates predictions for the future speed sequences. We evaluate our method on a dataset of 44,176 A321 flight samples. The experimental results show that the prediction accuracy of the proposed method is significantly higher than the conventional methods.

关键词： QAR data Landing speed prediction encoder-decoder Long short-term memory GBDT

来源：评论

学校读者我要写书评

暂无评论

Leveraging Linguistically-aware Object Relations and NASNet for Image Captioning 35

Leveraging Linguistically-aware Object Relations and NASNet ...

引用

35th International Conference on Image and Vision Computing New Zealand (IVCNZ)

作者： Sharif, Naeha Jalwana, Mohammad A. A. K. Bennamoun, Mohammed Liu, Wei Shah, Syed Afaq Ali Univ Western Australia Perth WA Australia Murdoch Univ Perth WA Australia

ISBN: (纸本)9781728185798

Image captioning is a challenging vision-to-language task, which has garnered a lot of attention over the past decade. The introduction of encoder-decoder based architectures expedited the research in this area and provided the backbone of the most recent systems. Moreover, leveraging relationships between objects for holistic scene understanding, which in turn improves captioning, has recently sparked interest among researchers. Our proposed model encodes the spatial and semantic proximity of object pairs into linguistically-aware relationship embeddings. Moreover, it captures the global semantics of the image using NASNet. This way, true semantic relations that are not apparent in visual content of an image can be learned, such that the decoder can attend to the most relevant object relations and visual features to generate more semantically-meaningful captions. Our experiments highlight the usefulness of linguistically-aware object relations as well as NASNet visual features for image captioning.

关键词： Image Captioning encoder-decoder Linguistically-aware object relationships NASNet

来源：评论

学校读者我要写书评

暂无评论

Sequence-level self-learning with multiple hypotheses 21

Sequence-level self-learning with multiple hypotheses

引用

Interspeech Conference

作者： Kumatani, Kenichi Dimitriadis, Dimitrios Gaur, Yashesh Gmyr, Robert Eskimez, Sefik Emre Li, Jinyu Zeng, Michael Microsoft Redmond WA 98052 USA

ISBN: (纸本)9781713820697

In this work, we develop new self-learning techniques with an attention-based sequence-to-sequence (seq2seq) model for automatic speech recognition (ASR). For untranscribed speech data, the hypothesis from an ASR system must be used as a label. However, the imperfect ASR result makes unsupervised learning difficult to consistently improve recognition performance especially in the case that multiple powerful teacher models are unavailable. In contrast to conventional unsupervised learning approaches, we adopt the multi-task learning (MTL) framework where the n-th best ASR hypothesis is used as the label of each task. The seq2seq network is updated through the MTL framework so as to find the common representation that can cover multiple hypotheses. By doing so, the effect of the hard-decision errors can be alleviated. We first demonstrate the effectiveness of our self-learning methods through ASR experiments in an accent adaptation task between the US and British English speech. Our experiment results show that our method can reduce the WER on the British speech data from 14.55% to 10.36% compared to the baseline model trained with the US English data only. Moreover, we investigate the effect of our proposed methods in a federated learning scenario.

关键词： unsupervised learning self-learning encoder-decoder multi-task learning end-to-end acoustic modeling

来源：评论

学校读者我要写书评

暂无评论

Denoising of Magnetic Resonance Images with Deep Neural Regularizer Driven by Image Prior 7

Denoising of Magnetic Resonance Images with Deep Neural Regu...

引用

7th IEEE International Conference on Data Science and Advanced Analytics (DSAA)

作者： Zhu, Yazhou Pan, Xiang Zhu, Jing Li, Lihua Liu, Yuan Jiangnan Univ Sch Artificial Intelligence & Comp Sci Wuxi Jiangsu Peoples R China Hangzhou Dianzi Univ Coll Life Informat Sci & Instrument Engn Hangzhou Peoples R China

ISBN: (纸本)9781728182063

Magnetic resonance imaging (MRI) is an important medical diagnosis technique in clinical diagnosis, while the quality of MR images is always damaged by the noise which is caused in the image acquisition process. In the classic image denoising methods, how to design an excellent regularizer with the prior knowledge of image is the key to solve the denoising problem. In this work, we introduce the deep neural regularizer for the MRI denoising tasks, the deep neural regularizer is made up of neural network structure and objective function, similar to the classic regularizer, both of these two parts are designed with the prior knowledge of image. The proposed neural network has three main parts: encoder network, decoder network and skip connections, the encoder network which consists of five down-sampling blocks is enforced to deeply extract low-resolution or highly-abstract MR image features, similar to the encoder network architecture, the decoder network is made up of five up-sampling blocks and is enforced to restore high-resolution MR image features. To generate more finer image features, we also use skip connections to transmit the abstract information from encoder to decoder directly. The objective function consists of data fidelity term and image quality penalty term, specifically, to enforce the capability of data fidelity term, we add the self-designed image structural consistency calculation to data fidelity term besides only calculating the image consistency over image pixels with mean squared error. Meanwhile, to guide the network generate more clearer image and reduce noise information, with the prior knowledge of image sharpness, an image quality penalty term which calculates the MR image sharpness is also added to the objective function. Experimental results over the simulated MRI data and real clinical data demonstrate the proposed network can achieve superior performance compared with other methods in terms of peak signal to noise ratio, structure simi

关键词： deep learning MRI denoising deep neural regularizer encoder-decoder objective function

来源：评论

学校读者我要写书评

暂无评论

Single headed attention based sequence-to-sequence model for state-of-the-art results on Switchboard 21

Single headed attention based sequence-to-sequence model for...

引用

Interspeech Conference

作者： Tuske, Zoltan Saon, George Audhkhasi, Kartik Kingsbury, Brian IBM Res AI Yorktown Hts NY 10598 USA Google Inc New York NY USA

ISBN: (纸本)9781713820697

It is generally believed that direct sequence-to-sequence (seq2seq) speech recognition models are competitive with hybrid models only when a large amount of data, at least a thousand hours, is available for training. In this paper, we show that state-of-the-art recognition performance can be achieved on the Switchboard-300 database using a single headed attention, LSTM based model. Using a cross-utterance language model, our single-pass speaker independent system reaches 6.4% and 12.5% word error rate (WER) on the Switchboard and CallHome subsets of Hub5'00, without a pronunciation lexicon. While careful regularization and data augmentation are crucial in achieving this level of performance, experiments on Switchboard-2000 show that nothing is more useful than more data. Overall, the combination of various regularizations and a simple but fairly large model results in a new state of the art, 4.8% and 8.3% WER on the Switchboard and CallHome sets, using SWB-2000 without any external data resources.

关键词： encoder-decoder attention speech recognition Switchboard

来源：评论

学校读者我要写书评

暂无评论

Cargo Segmentation in Stream of Commerce (SoC) X-Ray Images with Deep Learning Algorithms 5

Cargo Segmentation in Stream of Commerce (SoC) X-Ray Images ...

引用

Conference on Anomaly Detection and Imaging with X-Rays (ADIX) V

作者： Shen, Weicheng Tuszynski, Jaroslaw Leidos Inc Leidos Innovat Ctr Reston VA 20190 USA

ISBN: (纸本)9781510635869

Inspecting shipping containers using X-ray imagery is critical to safekeeping our borders. One of major tasks of inspecting shipping containers is manifest verification, which has two components: 1) determine what cargos are contained in a shipping container, which can be carried out in cargo segmentation, and 2) compare the cargos in the container with the cargos declared in the manifest. We focus our study on cargo segmentation. Cargo segmentation is the process of partitioning the cargo inside the container into regions with similar appearance. Assign a cargo class label to each pixel in the X-ray images. Our contribution is the development of a deep learning neural net based cargo segmentation algorithm that significantly improves the traditional ways of performing cargo segmentation. The cargo segmentation process is implemented by first partitioning the X-ray images into image tiles of certain sizes, and then train a deep learning (DL) model-based semantic segmentation algorithms using the annotated image tiles to partition the cargo into regions of similar appearance. The DL based semantic segmentation algorithm we used is an encoder-decoder structure often used for semantic segmentation. The DL network implementation chosen for our cargo segmentation is DeepLab v3+, which includes the atrous separable convolution composed of a depthwise convolution and pointwise convolution. Our X-ray cargo images used for development is a government-provided data set (GPD).

关键词： X-ray image cargo container deep learning semantic segmentation encoder-decoder atrous convolution

来源：评论

学校读者我要写书评

暂无评论

Automatic Tongue Crack Extraction For Real-Time Diagnosis

Automatic Tongue Crack Extraction For Real-Time Diagnosis

引用

IEEE International Conference on Bioinformatics and Biomedicine (IEEE BIBM)

作者： Peng, Jianqiang Li, Xinlei Yang, Dawei Zhang, Yingtao Zhang, Wei Zhang, Ye Kong, Yajie Li, Fufeng Zhang, Wenqiang Fudan Univ Acad Engn & Technol Shanghai Peoples R China Fudan Univ Shanghai Key Lab Intelligent Informat Proc Shanghai Peoples R China Chinese Acad Sci Changchun Inst Opt Fine Mech & Phys Changchun Peoples R China Shanghai Univ TCM Lab TCM Four Proc Shanghai Peoples R China

ISBN: (纸本)9781728162157

Tongue crack segmentation is an essential component of computer-aided diagnosis applied in Traditional Chinese Medicine (TCM). However, existing methods are inadequate when dealing with the vague boundary of the foreground and the variation of tongue images. To this end, we propose a P-shaped neural network architecture based on the lightweight encoder-decoder structure: the encoder transforms pixel position information into channel information by aggregating adjacent pixel values;the decoder restores the image size and obtains the refined pixel-level extraction results by integrating the information of the corresponding layer in the encoder. To further improve the utilization of network parameters and the model's generalization ability, we design three novel sub-modules: (1) the phantom module utilizes cheap operations to generate feature maps, speeding up the calculation;(2) the dual-input module increases the original input information to enhance the model's foreground understanding;(3) the dual attention gate module strengthens the information fusion of high-level and low-level feature maps, retaining good boundary information while capturing detail information. Additionally, we propose a pre-training method based on cropped patch images, which makes the model sensitive to details of the foreground before formal training. We demonstrate the model's effectiveness on our constructed dataset, achieving 60.6% IoU accuracy, and the segmentation of a 513x513 image takes 390 ms on CPU. And our dataset is available at https://***/pengjianqiang/FDU-TC.

关键词： Tongue Crack Segmentation Neural Network encoder-decoder Lightweight Attention

来源：评论

学校读者我要写书评

暂无评论

ERV-Net: An efficient 3D residual neural network for brain tumor segmentation

引用

EXPERT SYSTEMS WITH APPLICATIONS 2021年 170卷 114566-114566页

作者： Zhou, Xinyu Li, Xuanya Hu, Kai Zhang, Yuan Chen, Zhineng Gao, Xieping Xiangtan Univ Minist Educ Key Lab Intelligent Comp & Informat Proc Xiangtan 411105 Peoples R China Baidu Inc Beijing 100085 Peoples R China Chinese Acad Sci Inst Automat Beijing 100190 Peoples R China Xiangnan Univ Coll Med Imaging & Inspect Chenzhou Peoples R China

Brain tumors are the most aggressive and mortal cancers, which lead to short life expectancy. A reliable and efficient automatic or semi-automatic segmentation method is significant for clinical practice. In recent years, deep learning-based methods achieve great success in brain tumor segmentation. However, due to the limitation of parameters and computational complexity, there is still much room for improvement in these methods. In this paper, we propose an efficient 3D residual neural network (ERV-Net) for brain tumor segmentation, which has less computational complexity and GPU memory consumption. In ERV-Net, a computation-efficient network, 3D ShuffleNetV2, is firstly utilized as encoder to reduce GPU memory and improve the efficiency of ERV-Net, and then the decoder with residual blocks (Res-decoder) is introduced to avoid degradation. Furthermore, a fusion loss function, which is composed of Dice loss and Cross-entropy loss, is developed to solve the problems of network convergence and data imbalance. Moreover, a concise and effective post-processing method is proposed to refine the coarse segmentation result of ERV-Net. The experimental results on the dataset of multimodal brain tumor segmentation challenge 2018 (BRATS 2018) demonstrate that ERV-Net achieves the best performance with Dice of 81.8%, 91.21% and 86.62% and Hausdorff distance of 2.70 mm, 3.88 mm and 6.79 mm for enhancing tumor, whole tumor and tumor core, respectively. Besides, ERV-Net also achieves high efficiency compared to the state-of-the-art methods.

关键词： Brain tumor segmentation 3D convolutional neural network encoder-decoder Efficiency Lightweight Residual block

来源：评论

学校读者我要写书评

暂无评论

Thermal wave image deblurring based on depth residual network

引用

INFRARED PHYSICS & TECHNOLOGY 2021年 117卷 103847-103847页

作者： Jiang, Haijun Chen, Fei Liu, Xining Chen, Jesse Zhang, Kai Li Chen Univ Elect Sci & Technol 2006 Xiyuan Blvd Chengdu 611731 Peoples R China Nanjing Univ Sci & Technol 200 Xiaolingwei St Nanjing 210094 Peoples R China Novelteq Ltd 6 Xingzhi Rd Nanjing 210046 Peoples R China

Thermal wave imaging is a nondestructive testing (NDT) technology widely used to detect defects for various materials. It is important for quality control purposes to be able to clearly define the sizes of the defective areas. Due to the diffusive nature of thermal waves the acquired images contain varying degrees of blur depending on the depth of the defects, which severely affects the ability to define the defects. Conventional edge enhancement algorithms are hardly to achieve desirable results. Using deep convolutional neural network, we designed a deep residual network based on an encoder-decoder structure. Through the depth residual and skip-connection structures, we can effectively solve the vanishing gradient problem and improve the ability of feature extraction. The experimental results demonstrate that the proposed method shows superior performance over conventional image enhancement algorithms by providing richer information with higher contrast and more details.

关键词： Infrared thermography Thermal wave image Image deblurring Depth residual network encoder-decoder

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：