检索结果-内蒙古大学图书馆

Adversarial Action Prediction Networks

IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE 2020年第3期42卷 539-553页

作者： Kong, Yu Tao, Zhiqiang Fu, Yun Rochester Inst Technol B Thomas Golisano Coll Comp & Informat Sci Rochester NY 14623 USA Northeastern Univ Dept ECE Boston MA 02115 USA Northeastern Univ Coll CIS Boston MA 02115 USA

Different from after-the-fact action recognition, action prediction task requires action labels to be predicted from partially observed videos containing incomplete action executions. It is challenging because these partial videos have insufficient discriminative information, and their temporal structure is damaged. We study this problem in this paper, and propose an efficient and powerful deep network for learning representative and discriminative features for action prediction. Our approach exploits abundant sequential context information in full videos to enrich the feature representations of partial videos. This information is encoded in latent representations using a variational autoencoder (VAE), which are encouraged to be progress-invariant. Decoding such latent representations using another VAE, we can reconstruct missing information in the features extracted from partial videos. An adversarial learning scheme is adopted to differentiate the reconstructed features from the features directly extracted from full videos in order to well align their distributions. A multi-class classifier is also used to encourage the features to be discriminative. Our network jointly learns features and classifiers, and generates the features particularly optimized for action prediction. Extensive experimental results on UCF101, Sports-1M and BIT datasets demonstrate that our approach remarkably outperforms state-of-the-art methods, and shows significant speedup over these methods. Results also show that actions differ in their prediction characteristics;some actions can be correctly predicted even though only the beginning 10% portion of videos is observed.

关键词： Action prediction action recognition sequential context variational autoencoder adversarial learning

来源：评论

学校读者我要写书评

暂无评论

Aligning Discriminative and Representative Features: An Unsupervised Domain Adaptation Method for Building Damage Assessment

引用

IEEE TRANSACTIONS ON IMAGE PROCESSING 2020年 29卷 6110-6122页

作者： Li, Yundong Hu, Wei Li, Hongguang Dong, Han Zhang, Baochang Tian, Qing North China Univ Technol Sch Informat Sci & Technol Beijing 100144 Peoples R China Beihang Univ Unmanned Syst Res Inst Beijing 100191 Peoples R China Beihang Univ Sch Automat Sci & Elect Engn Beijing 100191 Peoples R China

Building assessment is highly prioritized during rescue operations and damage relief after hurricane disasters. Although machine learning has made remarkable improvement in building damage classification, it remains challenging because classifiers must be trained using a massive amount of labeled data. Furthermore, data labeling is labor intensive, costly, and unavailable after a disaster. To address this issue, we propose an unsupervised domain adaptation method with aligned discriminative and representative features (ADRF), which leverage a substantial amount of labeled data of relevant disaster scenes for new classification tasks. The remote sensing imageries of different disasters are collected using different sensors, viewpoints, times, even at various places. Compared with the public datasets used in the domain adaptation community, the remote sensing imageries are more complicated which exhibit characteristics of lower discrimination between categories and higher diversity within categories. As a result, pursuing domain invariance is a huge challenge. To achieve this goal, we build a framework with ADRF to improve the discriminative and representative capability of the extracted features to facilitate the classification task. The ADRF framework consists of three pipelines: a classifier for the labeled data of the source domain and one autoencoder each for the source and target domains. The latent variables of autoencoders are forced to observe unit Gaussian distributions by minimizing the maximum mean discrepancy (MMD), whereas the marginal distributions of both domains are aligned via the MMD. As a case study, two challenging transfer tasks using the hurricane Sandy, Maria, and Irma datasets are investigated. Experimental results demonstrate that ADRF achieves overall accuracy of 71.6% and 84.1% in the transfer tasks from dataset Sandy to dataset Maria and dataset Irma, respectively.

关键词： Building damage assessment domain adaptation MMD transfer learning variational autoencoder

来源：评论

学校读者我要写书评

暂无评论

A Study of Inductive Biases for Unsupervised Speech Representation Learning

引用

IEEE-ACM TRANSACTIONS ON AUDIO SPEECH AND LANGUAGE PROCESSING 2020年 28卷 2781-2795页

作者： Boulianne, Gilles Ctr Rech Informat Montreal CRIM Montreal PQ H3N 1M3 Canada Ecole Technol Super ETS Montreal PQ Canada

Distributed representations, or embeddings, are commonly learned without supervision on very large unannotated corpora for natural language processing. In speech processing, deep network-based representations such as bottlenecks and x-vectors have had some success,but are limited to supervised or partly supervised settings where annotations are available and are not optimized to separate underlying factors. Here, we propose a generative model with deep encoders and decoders that can learn interpretable speech representations without supervision. Our inductive biases operate as prior distributions in a variational autoencoder model and allow us to separate several latent variables along a continuous range of time-scale properties, as opposed to binary oppositions or hierarchical factorization that have been previously proposed. On simulated data, we confirm that these biases enable the model to accurately recover phonetic and speaker underlying factors. On TIMIT and LibriSpeech, they yield representations that separate phonetic and speaker information, as evidenced by unsupervised results on downstream phoneme and speaker classification tasks using a simple k-means classifier.

关键词： Speech processing Phonetics Task analysis Speech recognition Neural networks Decoding Unsupervised speech representation representation learning variational autoencoder

来源：评论

学校读者我要写书评

暂无评论

An advanced hybrid deep adversarial autoencoder for parameterized nonlinear fluid flow modelling

引用

COMPUTER METHODS IN APPLIED MECHANICS AND ENGINEERING 2020年 372卷 113375-113375页

作者： Cheng, M. Fang, F. Pain, C. C. Navon, I. M. Imperial Coll London Dept Earth Sci & Engn Appl Modelling & Computat Grp London SW7 2BP England Florida State Univ Dept Sci Comp Tallahassee FL 32306 USA

Considering the high computation cost required in conventional computation fluid dynamic simulations, machine learning methods have been introduced to flow dynamic simulations in years, aiming on reducing CPU time. In this work, we propose a hybrid deep adversarial autoencoder (VAE-GAN) to integrate generative adversarial network (GAN) and variational autoencoder (VAE) for predicting parameterized nonlinear fluid flows in spatial and temporal dimensions. High-dimensional inputs are compressed into the low-dimensional representations by nonlinear functions in a convolutional encoder. In this way, the predictive fluid flows reconstructed in a convolutional decoder contain the dynamic fluid flow physics of high nonlinearity and chaotic nature. In addition, the low-dimensional representations are applied to the adversarial network for model training and parameter optimization, which enables fast computation process. The capability of the hybrid VAE-GAN is illustrated by varying inputs on a flow past a cylinder test case as well as a second case of water column collapse. Numerical results show that this hybrid VAE-GAN has successfully captured the spatio-temporal flow features with CPU speed-up of three orders of magnitude. These promising results suggest that the hybrid VAE-GAN can play a critical role in efficiently and accurately predicting complex flows in future research efforts. (c) 2020 Elsevier B.V. All rights reserved.

关键词： Parameterized Nonlinear fluid flows Generative adversarial networks variational autoencoder Model reduction

来源：评论

学校读者我要写书评

暂无评论

Semi-supervised Cavitation Detection for Centrifugal Pumps

引用

TRANSACTIONS OF THE KOREAN SOCIETY OF MECHANICAL ENGINEERS A 2022年第2期46卷 153-162页

作者： Yoo, Donghwi Choi, Minseok Kim, Chungeon Oh, Hyunseok Gwangju Inst Sci & Technol Sch Mech Engn Gwangju South Korea

Cavitation is a dominant failure mode that accelerates the wear and deterioration of pumps. Cavitation can lead to pump malfunction and, eventually, catastrophic failure of the whole system. Therefore, it is important to avoid cavitation in the pump. This paper proposes a semi-supervised learning method that detects cavitation in centrifugal pumps. One-dimensional (1D) vibration signals are converted into two-dimensional (2D) images by the short time Fourier transform. The severity of the cavitation is determined using the variational autoencoder and Mahalanobis distance. The effectiveness of the proposed method is evaluated using the data collected from a 0.75 kW hydraulic pump testbed. It is confirmed that the proposed method can detect cavitation with different severities and help avoid the cavitation phenomenon.

关键词： Anomaly Detection Short Time Fourier Transform variational autoencoder Mahalanobis Distance

来源：评论

学校读者我要写书评

暂无评论

Cost-Sensitive variational Autoencoding Classifier for Imbalanced Data Classification

引用

ALGORITHMS 2022年第5期15卷 139-139页

作者： Liu, Fen Qian, Quan Shanghai Univ Sch Comp Engn & Sci Shanghai 200444 Peoples R China Shanghai Univ Mat Genome Inst Shanghai 200444 Peoples R China Zhejiang Lab Hangzhou 311100 Peoples R China

Classification is among the core tasks in machine learning. Existing classification algorithms are typically based on the assumption of at least roughly balanced data classes. When performing tasks involving imbalanced data, such classifiers ignore the minority data in consideration of the overall accuracy. The performance of traditional classification algorithms based on the assumption of balanced data distribution is insufficient because the minority-class samples are often more important than others, such as positive samples, in disease diagnosis. In this study, we propose a cost-sensitive variational autoencoding classifier that combines data-level and algorithm-level methods to solve the problem of imbalanced data classification. Cost-sensitive factors are introduced to assign a high cost to the misclassification of minority data, which biases the classifier toward minority data. We also designed misclassification costs closely related to tasks by embedding domain knowledge. Experimental results show that the proposed method performed the classification of bulk amorphous materials well.

关键词： variational autoencoder imbalanced data classification cost-sensitive learning

来源：评论

学校读者我要写书评

暂无评论

TLVANE: a two-level variation model for attributed network embedding

引用

NEURAL COMPUTING & APPLICATIONS 2020年第9期32卷 4835-4847页

作者： Huang, Zhichao Li, Xutao Ye, Yunming Li, Feng Liu, Feng Yao, Yuan Harbin Inst Technol Shenzhen Key Lab Internet Informat Collaborat Shenzhen Grad Sch Shenzhen Peoples R China

Network embedding aims to learn low-dimensional representations for nodes in social networks, which can serve many applications, such as node classification, link prediction and visualization. Most of network embedding methods focus on learning the representations solely from the topological structure. Recently, attributed network embedding, which utilizes both the topological structure and node content to jointly learn latent representations, becomes a hot topic. However, previous studies obtain the joint representations by directly concatenating the one from each aspect, which may lose the correlations between the topological structure and node content. In this paper, we propose a new attributed network embedding method, TLVANE, which can address the drawback by exploiting the deep variational autoencoders (VAEs). Particularly, a two-level VAE model is built, where the first-level accounts for the joint representations while the second for the embeddings of each aspect. Extensive experiments on three real-world datasets have been conducted, and the results demonstrate the superiority of the proposed method against state-of-the-art competitors.

关键词： Attribute network Embedding variational autoencoder

来源：评论

学校读者我要写书评

暂无评论

Speaker Anonymization for Personal Information Protection Using Voice Conversion Techniques

引用

IEEE ACCESS 2020年 8卷 198637-198645页

作者： Yoo, In-Chul Lee, Keonnyeong Leem, Seonggyun Oh, Hyunwoo Ko, Bonggu Yook, Dongsuk Korea Univ Dept Comp Sci & Engn Artificial Intelligence Lab Seoul 02841 South Korea

As speech-based user interfaces integrated in the devices such as AI speakers become ubiquitous, a large amount of user voice data is being collected to enhance the accuracy of speech recognition systems. Since such voice data contain personal information that can endanger the privacy of users, the issue of privacy protection in the speech data has garnered increasing attention after the introduction of the General Data Protection Regulation in the EU, which implies that restrictions and safety measures for the use of speech data become essential. This study aims to filter the speaker-related voice biometrics present in speech data such as voice fingerprint without altering the linguistic content to preserve the usefulness of the data while protecting the privacy of users. To achieve this, we propose an algorithm that produces anonymized speeches by adopting many-to-many voice conversion techniques based on variational autoencoders (VAEs) and modifying the speaker identity vectors of the VAE input to anonymize the speech data. We validated the effectiveness of the proposed method by measuring the speaker-related information and the original linguistic information retained in the resultant speech, using an open source speaker recognizer and a deep neural network-based automatic speech recognizer, respectively. Using the proposed method, the speaker identification accuracy of the speech data was reduced to 0.1-9.2%, indicating successful anonymization, while the speech recognition accuracy was maintained as 78.2-81.3%.

关键词： Data privacy deep neural networks speaker anonymization variational autoencoder voice conversion

来源：评论

学校读者我要写书评

暂无评论

Recurrent neural variational model for follower-based influence maximization

引用

INFORMATION SCIENCES 2020年 528卷 280-293页

作者： Huang, Huimin Meng, Zaiqiao Liang, Shangsong Sun Yat Sen Univ Sch Data & Comp Sci Guangzhou Peoples R China Univ Glasgow Glasgow Lanark Scotland

Influence Maximization, aiming at selecting a small set of seed users in a social network to maximize the spread of influence, has attracted considerable attention recently. Most of the existing influence maximization algorithms focus on the diffusion model of one single-entity, which assumes that only one entity is propagated by users in social network. However, the diffusion situations in real world social networks often involve multiple entities, competitive or complementary, spreading through the whole network, and are more complex than the situations of single independent entity. In this paper, we propose a novel optimization problem, namely, the follower-based influence maximization, which aims to promote a new product into the market by maximizing the influence of a social network where other competitive and complementary products have already been propagating. We tackle this problem by proposing a Recurrent Neural variational model (RNV) and a follower-based greedy algorithm (RNVGA). The RNV model dynamically tracks entity correlations and cascade correlations through a deep generative model and recurrent neural variational inference, while the RNVGA algorithm applies the greedy approach for submodular maximization and efficiently computes the seed node set for the target product. Extensive experiments have been conducted to evaluate effectiveness and efficiency of our method, and the results show the superiority of our method compared with the state-of-the-art methods. (C) 2020 Elsevier Inc. All rights reserved.

关键词： Recurrent neural network variational autoencoder Influence diffusion Social networks

来源：评论

学校读者我要写书评

暂无评论

variational Deep Clustering of Wafer Map Patterns

引用

IEEE TRANSACTIONS ON SEMICONDUCTOR MANUFACTURING 2020年第3期33卷 466-475页

作者： Hwang, Jonghyun Kim, Heeyoung Korea Adv Inst Sci & Technol Dept Ind & Syst Engn Daejeon 34141 South Korea

In semiconductor manufacturing, several measurement data called wafer maps are obtained in the metrology steps, and the variations in the process are detected by analyzing the wafer map data. Hidden processes or equipment affecting the process quality variations can be found by comparing the process tracking history and clustered groups of similar wafer maps;thus, clustering analysis is very important to reduce the process quality variations. Currently, clustering wafer maps are becoming more difficult as the wafer maps are formed into more complex patterns along with high-dimensional data. For more effective clustering of complex and high-dimensional wafer maps, we implement a Gaussian mixture model to a variational autoencoder framework to extract features that are more suitable to the clustering environment, and a Dirichlet process is further applied in the variational autoencoder mixture framework for automated one-step clustering. The proposed method is validated using a real dataset from a global semiconductor manufacturing company, and we demonstrate that it is more effective than other competitive methods in determining the number of clusters and clustering wafer map patterns.

关键词： Bayesian nonparametrics clustering deep neural network Dirichlet process Gaussian mixture model semiconductor manufacturing variational autoencoder

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：