检索结果-内蒙古大学图书馆

encoder-decoder with double spatial pyramid for semantic segmentation

JOURNAL OF ELECTRONIC IMAGING 2019年第6期28卷 063007-063007页

作者： Kong, Huifang Hu, Jie Fan, Lei Zhang, Xiaoxue Fang, Yao Hefei Univ Technol Sch Elect Engn & Automat Hefei Anhui Peoples R China

Semantic segmentation, as a dense pixelwise classification task, is of great significance to scene understanding. Many approaches based on convolutional neural network still suffer from two kinds of challenges: (1) insufficient semantic information results in semantic obfuscation between similar categories, (2) loss of spatial information leads to inaccurate location of inconspicuous objects. To tackle these challenges, we design a network with an encoder-decoder architecture based on two proposed modules: global pyramid attention module (GPAM) and pyramid decoder module (PDM). Specifically, GPAM exploits an attention mechanism as global prior knowledge to adaptively capture discriminative features for enhancing semantic representation, and PDM employs small convolutions connected in parallel to predict adjacent position relationships for refining spatial information. A series of ablation experiments are conducted to demonstrate the effectiveness of our designs, and our network achieves a mean intersection over union score of 83.4% on PASCAL VOC 2012 dataset and 78.5% on Cityscapes dataset. (C) 2019 SPIE and IS&T

关键词： semantic segmentation encoder-decoder spatial pyramid attention mechanism

来源：评论

学校读者我要写书评

暂无评论

MMSpeech: Multi-modal Multi-task encoder-decoder Pre-training for speech recognition 24

MMSpeech: Multi-modal Multi-task Encoder-Decoder Pre-trainin...

引用

Interspeech Conference

作者： Zhou, Xiaohuan Wang, Jiaming Cui, Zeyu Zhang, Shiliang Yan, Zhijie Zhou, Jingren Zhou, Chang DAMO Acad Alibaba Grp Beijing Peoples R China

In this paper, we propose a novel multi-modal multi-task encoder-decoder pre-training framework (MMSpeech) for Mandarin automatic speech recognition (ASR), which employs both unlabeled speech and text data. The main difficulty in speech-text joint pre-training comes from the significant difference between speech and text modalities, especially for Mandarin speech and text. Unlike English and other languages with an alphabetic writing system, Mandarin uses an ideographic writing system where character and sound are not tightly mapped to one another. Therefore, we propose to introduce the phoneme modality into pre-training, which can help capture modality-invariant information between Mandarin speech and text. In addition, a much larger amount of unsupervised text data 292G is utilized for pre-training, which brings significant improvements. Experiments on AISHELL-1 show that our proposed method achieves state-of-the-art performance, with a more than 40% relative improvement.

关键词： ASR pre-training encoder-decoder

来源：评论

学校读者我要写书评

暂无评论

Multitask Learning with Low-Level Auxiliary Tasks for encoder-decoder Based Speech Recognition 18

Multitask Learning with Low-Level Auxiliary Tasks for Encode...

引用

18th Annual Conference of the International-Speech-Communication-Association (INTERSPEECH 2017)

作者： Toshniwal, Shubham Tang, Hao Lu, Liang Livescu, Karen Toyota Technol Inst Chicago IL 60637 USA

ISBN: (纸本)9781510848764

End-to-end training of deep learning-based models allows for implicit learning of intermediate representations based on the final task loss. However, the end-to-end approach ignores the useful domain knowledge encoded in explicit intermediate-level supervision. We hypothesize that using intermediate representations as auxiliary supervision at lower levels of deep networks may be a good way of combining the advantages of end-to-end training and more traditional pipeline approaches. We present experiments on conversational speech recognition where we use lower-level tasks, such as phoneme recognition, in a multitask training approach with an encoder-decoder model for direct character transcription. We compare multiple types of lower-level tasks and analyze the effects of the auxiliary tasks. Our results on the Switchboard corpus show that this approach improves recognition accuracy over a standard encoder-decoder model on the Eva12000 test set.

关键词： speech recognition multitask learning encoder-decoder CTC LSTM

来源：评论

学校读者我要写书评

暂无评论

encoder-decoder neural networks for predicting future FTIR spectra - application to enzymatic protein hydrolysis

引用

JOURNAL OF BIOPHOTONICS 2022年第9期15卷 e202200097-e202200097页

作者： Kuchta, Miroslav Wubshet, Sileshi Gizachew Afseth, Nils Kristian Mardal, Kent-Andre Liland, Kristian Hovde Simula Res Lab Dept Sci Comp & Numer Anal Oslo Norway Nofima Norwegian Inst Food Fisheries & Aquaculture Res As Norway Univ Oslo Dept Math Oslo Norway Norwegian Univ Life Sci Dept Sci & Technol As Norway

In the process of converting food-processing by-products to value-added ingredients, fine grained control of the raw materials, enzymes and process conditions ensures the best possible yield and economic return. However, when raw material batches lack good characterization and contain high batch variation, online or at-line monitoring of the enzymatic reactions would be beneficial. We investigate the potential of deep neural networks in predicting the future state of enzymatic hydrolysis as described by Fourier-transform infrared spectra of the hydrolysates. Combined with predictions of average molecular weight, this provides a flexible and transparent tool for process monitoring and control, enabling proactive adaption of process parameters.

关键词： deep learning encoder-decoder enzymatic protein hydrolysis FTIR process control

来源：评论

学校读者我要写书评

暂无评论

Tweet2Vec: Learning Tweet Embeddings Using Character-level CNN-LSTM encoder-decoder 16

Tweet2Vec: Learning Tweet Embeddings Using Character-level C...

引用

39th International ACM SIGIR conference on Research and Development in Information Retrieval

作者： Vosoughi, Soroush Vijayaraghavan, Prashanth Roy, Deb MIT Media Lab Cambridge MA 02139 USA

ISBN: (纸本)9781450340694

We present Tweet2Vec, a novel method for generating general-purpose vector representation of tweets. The model learns tweet embeddings using character-level CNN-LSTMencoder-decoder. We trained our model on 3 million, randomly selected English-language tweets. The model was evaluated using two methods: tweet semantic similarity and tweet sentiment categorization, outperforming the previous state-of-the-art in both tasks. The evaluations demonstrate the power of the tweet embeddings generated by our model for various tweet categorization tasks. The vector representations generated by our model are generic, and hence can be applied to a variety of tasks. Though the model presented in this paper is trained on English-language tweets, the method presented can be used to learn tweet embeddings for different languages.

关键词： Twitter Embedding Tweet Convolutional Neural Networks CNN LSTM Tweet2Vec encoder-decoder

来源：评论

学校读者我要写书评

暂无评论

Enhancing Peatland Classification using Sentinel-1 and Sentinel-2 Fusion with encoder-decoder Architecture 27

Enhancing Peatland Classification using Sentinel-1 and Senti...

引用

27th International Conference on Information Fusion (FUSION)

作者： Zelioli, Luca Farahnakian, Fahimeh Farahnakian, Farshad Middleton, Maarit Heikkonen, Jukka Univ Turku Dept Comp Turku Finland Geol Survey Finland GTK Espoo Finland

ISBN: (纸本)9798350371420;9781737749769

Peatland classification provides valuable information for greenhouse gas inventory and biodiversity protection. In this paper, we proposed an encoder-decoder-based architecture for peatland classification that fuses two open-source satellite data, Sentinel-1 and Sentinel-2. We show the effect of fusion by comparing the multi-modal fusion architecture with uni-modals which are trained only based on one input data source. We also investigate the influence of skip connections as the main component of the encoder-decoder to recover fine-grained details that are lost during the downsampling process. The experimental results are acquired on a study area in Finland which covers a variety minerotrophic aapa mire peatlands. The results demonstrate that multi-modal architecture consistently outperforms uni-modal architectures for peatland classification. In addition, the fusion architecture with one skip connection achieved a total accuracy of 57.44%. This shows 8.51% accuracy improvement compared with the model without skip connections.

关键词： encoder-decoder data fusion peatland classification skip connections remote sensing land cover classification

来源：评论

学校读者我要写书评

暂无评论

Optimizing FPGA-based Convolutional encoder-decoder Architecture for Semantic Segmentation 9

Optimizing FPGA-based Convolutional Encoder-Decoder Architec...

引用

9th IEEE Annual International Conference on Cyber Technology in Automation, Control, and Intelligent Systems (IEEE-CYBER)

作者： Yu, Mengqi Huang, Hongzhi Liu, Hong He, Shuyi Qiao, Fei Luo, Li Xie, Fugui Liu, Xin-Jun Yang, Huazhong Tsinghua Univ Dept Elect Engn BNRist Beijing Peoples R China Beijing Jiaotong Univ Sch Elect & Informat Engn Beijing Peoples R China Beijing Jiaotong Univ Sch Comp & Informat Technol Beijing Peoples R China Tsinghua Univ Dept Mech Engn Beijing Peoples R China

ISBN: (纸本)9781728107707

Convolutional neural networks (CNNs) for visual semantic segmentation have been attracting considerable attention recently because of their superior support for many significant tasks, such as autonomous driving, semantic SLAM (simultaneous localization and mapping) and remote sensing surveying and mapping. These kinds of applications generally need to he implemented on the smart terminals, which means that a kind of hardware platform with high energy efficiency and real-time performance is required. However, CNNs for semantic segmentation usually contain sonic, symmetrical encoders and decoders, corresponding to the down-sampling process (e.g., pooling, convolution) and the up-sampling process (e.g., unpooling, deconvolution). All of these processes are computing and storage intensive, which limits their applicability in the resource constrained embedded systems. In this paper, an FPGA-based accelerator programed by OpenCL is proposed. We evaluate its performance on the CamVid dataset. The global accuracy only drops by 2.04% with 8-bit quantization. Additionally, the system shows 48.89 GOPS and 2.4x real-time performance against CPU when running on an Arria-10 GX1150 device.

关键词： FPGA Convolutional Neural Networks encoder-decoder Semantic Segmentation Accelerator

来源：评论

学校读者我要写书评

暂无评论

A method of face repair based on encoder-decoder and dual discrimination network 39

A method of face repair based on encoder-decoder and dual di...

引用

39th Chinese Control Conference (CCC)

作者： Cui Can Zhao Jun Xiong Xingzhong Edwards, Nathaniel O. Sichuan Univ Sci & Engn Yinbin Peoples R China

ISBN: (纸本)9789881563903

Neural networks have made significant achievements in the field of image restoration. To efficiently repair facial images with large areas damaged, a decoder-encoder structured convolutional neural network is used as a generative model and skip-connection is added between some of its layers to enhance the structure prediction ability of the generated model and well suppressed the problem that the repair network is easy to over-fitting. The global discrimination network mostly uses the image's edge structure and feature information to ensure that the repaired image, which is the output from the repair network, conforms to visual connectivity, while the local discriminators, not only recognize local consistency but also optimize more details. The network structure proposed in this paper combines the encoder-decoder, skip-connection, and dual discriminator networks to improve the effect of face completion. The experimental results on the CelebA show that the proposed method is superior to other methods in repairing images with large areas of damage.

关键词： Generative Adversarial Network (GAN) face inpainting skip-connection encoder-decoder global and local discriminators

来源：评论

学校读者我要写书评

暂无评论

ProDE: Interpretable APT Detection Method Based on encoder-decoder Architecture 29

ProDE: Interpretable APT Detection Method Based on Encoder-d...

引用

29th IEEE International Conference on Parallel and Distributed Systems, ICPADS 2023

作者： Zhou, Fengxi Chang, Baoming Wen, Yu Meng, Dan University of Chinese Academy of Sciences Institute of Information Engineering Chinese Academy of Sciences School of Cyber Security Beijing China Chinese Academy of Sciences Institute of Information Engineering Beijing China

ISBN: (纸本)9798350330717

The detection and analysis of Advanced Persistent Threats (APTs) are pivotal for contemporary network security. Provenance graphs, constructed from audit logs, offer a wealth of contextual information to identify and analyze threats and are popular in APT detection field. However, existing approaches frequently fall short in offering explanatory capabilities for their detection results, placing an additional burden on security analysts. Confronted with coarse-grained detection outcomes, analysts must delve into provenance graphs or audit logs to precisely pinpoint attack entities and events, which can significantly delay the response to threats. In this paper, we propose ProDE, a novel approach that enhances APT detection by providing interpretable results using an encoder-decoder architecture. ProDE initiates the detection process by comparing the encoded representations of the true graph and the predicted graph. Upon detecting abnormalities, the encoder-decoder model is able to decode the encodings into provenance graphs, thereby revealing inconsistencies between the decoded graph and real graph that serve as interpretable results. We evaluate ProDE on two widely used datasets, while taking into account the detection performance, the result shows ProDE can provided the more detailed detection results which provide the interpretation for analysts compared with existing approaches. © 2023 IEEE.

关键词： Advanced Persistent Threats (APTs) encoder-decoder interpretable

来源：评论

学校读者我要写书评

暂无评论

encoder-decoder graph neural network for credit card fraud detection

引用

JOURNAL OF KING SAUD UNIVERSITY-COMPUTER AND INFORMATION SCIENCES 2024年第3期36卷

作者： Cherif, Asma Ammar, Heyfa Kalkatawi, Manal Alshehri, Suhair Imine, Abdessamad King Abdulaziz Univ Fac Comp & Informat Technol Dept Informat Technol Jeddah Saudi Arabia King Abdulaziz Univ Ctr Excellence Smart Environm Res Jeddah Saudi Arabia Prince Sultan Univ Riyadh Saudi Arabia Univ Tunis Almanar Natl Engn Sch Tunis RISC ENIT Res Lab Tunis Tunisia Univ Lorraine CNRS INRIA Nancy France

Credit card fraud is a significant problem, with millions of dollars lost each year. Detecting fraudulent transactions is a challenging task due to the large volume of data and the constantly evolving tactics of fraudsters. Likewise any detection problem, it is important to select relevant features that help distinguishing between fraudulent and non -fraudulent transactions. It is also crucial to design a model that effectively captures the relationships between involved entities such as merchants and customers. In this work, a prior stage of feature engineering is carried out. Then, the use of the Graph Neural Networks (GNNs) for credit card fraud detection is explored by leveraging the relationships between customers and merchants. We propose a novel encoder-decoder based GNNs that effectively captures the complex relationships and dependencies within credit card transaction data. The performance of the model is further improved by employing a graph converter for efficient graph data processing and batch normalization for reducing internal covariate shift and accelerating convergence. Our experiments on a large scale dataset delivered promising results that outperform other models in terms of precision, recall, and F1 score.

关键词： Credit card fraud detection Graph neural networks encoder-decoder Feature engineering Deep learning

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：