检索结果-内蒙古大学图书馆

27th International Conference on Neural Information Processing

作者： Li, Qian Guo, Nan Ye, Xiaochun Fan, Dongrui Tang, Zhimin Chinese Acad Sci Inst Comp Technol State Key Lab Comp Architecture Beijing Peoples R China Univ Chinese Acad Sci Beijing Peoples R China

ISBN: (纸本)9783030638191;9783030638207

Recently, many methods have been proposed for object detection. However, they cannot detect objects by semantic features, adaptively. According to channel and spatial attention mechanisms, we mainly analyze that different methods detect objects adaptively. Some state-of-the-art detectors combine different feature pyramids with many mechanisms. However, they require more cost. This work addresses that by an anchor-free detector with shared encoder-decoder with attention mechanism, extracting shared features. We consider features of different levels from backbone (e.g., ResNet-50) as the basis features. Then, we feed the features into a simple module, followed by a detector header to detect objects. Meantime, we use the semantic features to revise geometric locations, and the detector is a pixel-semantic revising of position. More importantly, this work analyzes the impact of different pooling strategies (e.g., mean, maximum or minimum) on multi-scale objects, and finds the minimum pooling can improve detection performance on small objects better. Compared with state-of-the-art MNC based on ResNet-101 for the standard MSCOCO 2014 baseline, our method improves detection AP of 3.8%.

关键词： Detection encoder-decoder Attention mechanism Pooling

来源：评论

学校读者我要写书评

暂无评论

基于encoder-decoder-ILSTM模型的瓦斯浓度预测研究

引用

能源与节能 2023年第12期 102-105,176页

作者：陈小建山西新景矿煤业有限公司山西阳泉045000

近年来,神经网络在各领域均发挥了巨大作用,同样在煤矿瓦斯浓度预测当中也有应用。为了提高模型的预测精度和实时性,结合encoder-decoder结构、长短期记忆形成、蛇优化算法提出了一种新的神经网络,为促进煤矿安全生产提供了技术支持。

关键词：神经网络 encoder-decoder 蛇优化算法瓦斯浓度预测

来源：评论

学校读者我要写书评

暂无评论

Confidence measures in encoder-decoder models for speech recognition 21

Confidence measures in encoder-decoder models for speech rec...

引用

Interspeech Conference

作者： Woodward, Alejandro Bonnin, Clara Masuda, Issey Varas, David Bou-Balust, Elisenda Riveiro, Juan Carlos Vilynx Menlo Pk CA 94025 USA

ISBN: (纸本)9781713820697

Recent improvements in Automatic Speech Recognition (ASR) systems have enabled the growth of myriad applications such as voice assistants, intent detection, keyword extraction and sentiment analysis. These applications, which are now widely used in the industry, are very sensitive to the errors generated by ASR systems. This could be overcome by having a reliable confidence measurement associated to the predicted output. This work presents a novel method which uses internal neural features of a frozen ASR model to train an independent neural network to predict a softmax temperature value. This value is computed in each decoder time step and multiplied by the logits in order to redistribute the output probabilities. The resulting softmax values corresponding to predicted tokens constitute a more reliable confidence measure. Moreover, this work also studies the effect of teacher forcing on the training of the proposed temperature prediction module. The output confidence estimation shows an improvement of -25.78% in EER and +7.59% in AUC-ROC with respect to the unaltered softmax values of the predicted tokens, evaluated on a proprietary dataset consisting on News and Entertainment videos.

关键词： speech recognition encoder-decoder confidence

来源：评论

学校读者我要写书评

暂无评论

Robust Beam Search for encoder-decoder Attention Based Speech Recognition without Length Bias 21

Robust Beam Search for Encoder-Decoder Attention Based Speec...

引用

Interspeech Conference

作者： Zhou, Wei Schluter, Ralf Ney, Hermann Rhein Westfal TH Aachen Human Language Technol & Pattern Recognit Comp Sci Dept D-52074 Aachen Germany AppTek GmbH D-52062 Aachen Germany

ISBN: (纸本)9781713820697

As one popular modeling approach for end-to-end speech recognition, attention-based encoder-decoder models are known to suffer the length bias and corresponding beam problem. Different approaches have been applied in simple beam search to ease the problem, most of which are heuristic-based and require considerable tuning. We show that heuristics are not proper modeling refinement, which results in severe performance degradation with largely increased beam sizes. We propose a novel beam search derived from reinterpreting the sequence posterior with an explicit length modeling. By applying the reinterpreted probability together with beam pruning, the obtained final probability leads to a robust model modification, which allows reliable comparison among output sequences of different lengths. Experimental verification on the LibriSpeech corpus shows that the proposed approach solves the length bias problem without heuristics or additional tuning effort. It provides robust decision making and consistently good performance under both small and very large beam sizes. Compared with the best results of the heuristic baseline, the proposed approach achieves the same WER on the 'clean' sets and 4% relative improvement on the 'other' sets. We also show that it is more efficient with the additional derived early stopping criterion.

关键词： speech recognition encoder-decoder beam search length bias

来源：评论

学校读者我要写书评

暂无评论

DENSIFICATION OF AIRBORNE LIDAR POINT CLOUD WITH FUSED encoder-decoder NETWORKS

DENSIFICATION OF AIRBORNE LIDAR POINT CLOUD WITH FUSED ENCOD...

引用

IEEE International Geoscience and Remote Sensing Symposium (IGARSS)

作者： Wang, Weimin Vinayaraj, Poliyapram Nakamura, Ryosuke Natl Inst Adv Ind Sci & Technol Tokyo Japan AIST Tokyo Tech Real World Big Data Computat Open Tokyo Japan

ISBN: (纸本)9781728163741

This paper presents a density enhancement method for airborne LiDAR point cloud with the corresponding image based on a fused encoder-decoder network. Different from terrestrial indoor or outdoor scenes, the variance of objects and depth ranges in the large scale airborne data is challenging. To address the problem of objects at different scales, we propose a RGB and depth fused encoder-decoder structure inspired by UNet. In addition, we propose a heuristic method for refining the result if instance segmentation labels are available. Both quantitative and qualitative evaluations are performed on a dataset covering 24km(2) area of Osaka in Japan validates the feasibility of the proposed method for densification of point cloud in large scale environment.

关键词： Densification Airborne LiDAR Point cloud UNet encoder-decoder Remote sensing

来源：评论

学校读者我要写书评

暂无评论

Drug Reaction Discriminator within encoder-decoder Neural Network Model: COVID-19 Pandemic Case Study 7

Drug Reaction Discriminator within Encoder-Decoder Neural Ne...

引用

7th International Conference on Social Networks Analysis, Management and Security (SNAMS)

作者： Grissette, Hanane Nfaoui, El Habib Sidi Mohamed Ben Abdellah Univ Fac Sci LISAC Lab Fes Morocco

ISBN: (纸本)9780738111803

Social networks become widely used for understanding patients shared experiences, and reaching a vast audience in a matter of seconds. In particular, many health-related organizations used sentiment analysis to automatically reporting treatment issues, drug misuse, new infectious disease symptoms. Few approaches have proposed in this matter, especially for detecting different drug reaction descriptions from patients generated narratives on social networks. Most of them consisted of only detecting adverse drug reaction(ADR), but may fail to retrieve other aspect, e.g, the beneficial drug reaction or drug retroviral effects such as "relieve intraocular pressure associated with glaucoma". In this study, we propose to develop an encoder-decoder for drug reaction discrimination that involves an enhanced distributed biomedical representation from controlled medical vocabulary such as PubMed and Clinical note MIMIC III. The embedding mechanism primarily leverages contextual information and learn from predefined clinical relationships in term of medical conditions in order to define possible drug reaction of individual meaning and multi-word expressions in the field of distributional semantics configuration that clarifies sentence's similarity in the same contextual target space, which are further share semantically common drug description meanings. Furthermore, the bidirectional sentiment inductive model are created to enhance drug reactions vectorization from real-world patients description whereby achieved higher performance in terms of disambiguating false positive and/or negative assessments. As a result, we achieved an 85.2% accuracy performance and the architecture shows a well-encoding of real-world drug entities descriptions.

关键词： Biomedical distributed representation Drug reaction encoder-decoder medical concepts Sentiment information

来源：评论

学校读者我要写书评

暂无评论

DeepSEED: 3D Squeeze-and-Excitation encoder-decoder Convolutional Neural Networks for Pulmonary Nodule Detection 17

DeepSEED: 3D Squeeze-and-Excitation Encoder-Decoder Convolut...

引用

IEEE 17th International Symposium on Biomedical Imaging (ISBI)

作者： Li, Yuemeng Fan, Yong Univ Penn Ctr Biomed Image Comp & Analyt Perelman Sch Med Dept Radiol Philadelphia PA 19104 USA

ISBN: (纸本)9781538693308

Pulmonary nodule detection plays an important role in lung cancer screening with low-dose computed tomography (CT) scans. It remains challenging to build nodule detection deep learning models with good generalization performance due to unbalanced positive and negative samples. In order to overcome this problem and further improve state-of-the-art nodule detection methods, we develop a novel deep 3D convolutional neural network with an encoder-decoder structure in conjunction with a region proposal network. Particularly, we utilize a dynamically scaled cross entropy loss to reduce the false positive rate and combat the sample imbalance problem associated with nodule detection. We adopt the squeeze-and-excitation structure to learn effective image features and utilize inter-dependency information of different feature maps. We have validated our method based on publicly available CT scans with manually labelled ground-truth obtained from LIDC/IDRI dataset and its subset LUNA16 with thinner slices. Ablation studies and experimental results have demonstrated that our method could outperform state-of-the-art nodule detection methods by a large margin.

关键词： Deep convolutional networks squeeze-and-excitation encoder-decoder lung nodule detection

来源：评论

学校读者我要写书评

暂无评论

Multi-Shell D-MRI Reconstruction via Residual Learning utilizing encoder-decoder Network with Attention (MSR-Net) 42

Multi-Shell D-MRI Reconstruction via Residual Learning utili...

引用

42nd Annual International Conference of the IEEE-Engineering-in-Medicine-and-Biology-Society (EMBC)

作者： Jha, Ranjeet Ranjan Nigam, Aditya Bhavsar, Arnav Pathak, Sudhir K. Schneider, Walter Rathish, K. Indian Inst Technol Mandi Sch Comp & Elect Engn SCEE Mandi Himachal Prades India Univ Pittsburgh Learning Res & Dev Ctr Pittsburgh PA 15260 USA Indian Inst Technol Kanpur Dept Math & Stat Kanpur Uttar Pradesh India

ISBN: (纸本)9781728119908

Contemporary diffusion MRI based analysis with HARDI, which provides more accurate fiber orientation, can be performed using single or multiple b-values (single or multi-shell). Single shell HARDI cannot provide volume fraction for different tissue types, which can produce bias and noisier results in estimation of fiber ODF. Multi-shell acquisition can resolve this issue. However, it requires more scanning time and is therefore not very well suited in clinical setting. Considering this, we propose a novel deep learning architecture, MSR-Net, for reconstruction of diffusion MRI volumes for some b-value using acquisitions at another b-value. In this work, we demonstrate this for b = 2000 s/mm(2) and b = 1000 s/mm(2). We learn such a transformation in the space of spherical harmonic coefficients. The proposed network consists of encoder-decoder along-with an attention module and a feature module. We have considered L2 and Content loss for optimizing and improving the performance. We have trained and validated the network using the HCP data-set with standard qualitative and quantitative performance measures.

关键词： Diffusion MRI Multi-shell HARDI encoder-decoder Content Loss Attention module Feature module

来源：评论

学校读者我要写书评

暂无评论

HYPERSPECTRAL IMAGE CLASSIFICATION VIA MULTI-SCALE encoder-decoder NETWORK

HYPERSPECTRAL IMAGE CLASSIFICATION VIA MULTI-SCALE ENCODER-D...

引用

IEEE International Geoscience and Remote Sensing Symposium (IGARSS)

作者： Ma, Jingjing Wu, Linlin Tang, Xu Zhang, Xiangrong Zhu, Cheng Ma, Junyong Jiao, Licheng Xidian Univ Sch Elect Engn Sch Artificial Intelligence Xian 710071 Shaanxi Peoples R China Sci & Technol Electroopt Control Lab Luoyang 471023 Peoples R China Xidian Univ Sch Artificial Intelligence Xian Peoples R China Xidian Univ Sch Elect Engn Xian Peoples R China

ISBN: (纸本)9781728163741

Hyperspectral image (HSI) classification is an important task in the remote sensing community. In general, many hyperspectral classification methods are based on pixel patch, which leads to information redundancy. In this paper, we propose a multi-scale encoder-decoder network for HSI classification. First, we adapt an encoder-decoder framework as the backbone network and use a skip connection between the encoder and decoder, the spatial information is obtained by this network. Second, we develop a multi-scale block to get the multi-scale information. Third, we retain complete spectral information through the constant number of spectral channels. Finally, an optimizer strategy is designed to achieve our model for the HSI classification task. We experiment with our method and other methods on two public datasets, and the results denote our model is useful for HSI classification task.

关键词： Hyperspectral image classification encoder-decoder multi-scale

来源：评论

学校读者我要写书评

暂无评论

Attention and encoder-decoder based models for transforming articulatory movements at different speaking rates 21

Attention and Encoder-Decoder based models for transforming ...

引用

Interspeech Conference

作者： Singh, Abhayjeet Illa, Aravind Ghosh, Prasanta Kumar Indian Inst Sci IISc Elect Engn Bangalore 560012 Karnataka India

ISBN: (纸本)9781713820697

While speaking at different rates, articulators (like tongue, lips) tend to move differently and the enunciations are also of different durations. In the past, affine transformation and DNN have been used to transform articulatory movements from neutral to fast(N2F) and neutral to slow(N2S) speaking rates [1]. In this work, we improve over the existing transformation techniques by modeling rate specific durations and their transformation using AstNet, an encoder-decoder framework with attention. In the current work, we propose an encoder-decoder architecture using LSTMs which generates smoother predicted articulatory trajectories. For modeling duration variations across speaking rates, we deploy attention network, which eliminates the need to align trajectories in different rates using DTW. We perform a phoneme specific duration analysis to examine how well duration is transformed using the proposed AstNet. As the range of articulatory motions is correlated with speaking rate, we also analyze amplitude of the transformed articulatory movements at different rates compared to their original counterparts, to examine how well the proposed AstNet predicts the extent of articulatory movements in N2F and N2S. We observe that AstNet could model both duration and extent of articulatory movements better than the existing transformation techniques resulting in more accurate transformed articulatory trajectories.

关键词： encoder-decoder Attention LSTM Speaking rate Electromagnetic Articulography

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：