检索结果-内蒙古大学图书馆

Deep Incremental Learning for Efficient High-Fidelity Face Tracking

ACM TRANSACTIONS ON GRAPHICS 2018年第6期37卷 234-234页

作者： Wu, Chenglei Shiratori, Takaaki Sheikh, Yaser Facebook Real Labs Pittsburgh PA 15213 USA

In this paper, we present an incremental learning framework for efficient and accurate facial performance tracking. Our approach is to alternate the modeling step, which takes tracked meshes and texture maps to train our deep learning-based statistical model, and the tracking step, which takes predictions of geometry and texture our model infers from measured images and optimize the predicted geometry by minimizing image, geometry and facial landmark errors. Our Geo-Tex VAE model extends the convolutional variational autoencoder for face tracking, and jointly learns and represents deformations and variations in geometry and texture from tracked meshes and texture maps. To accurately model variations in facial geometry and texture, we introduce the decomposition layer in the Geo-Tex VAE architecture which decomposes the facial deformation into global and local components. We train the global deformation with a fully-connected network and the local deformations with convolutional layers. Despite running this model on each frame independently - thereby enabling a high amount of parallelization - we validate that our framework achieves sub-millimeter accuracy on synthetic data and outperforms existing methods. We also qualitatively demonstrate high-fidelity, long-duration facial performance tracking on several actors.

关键词： facial performance tracking variational autoencoder

来源：评论

学校读者我要写书评

暂无评论

A One-Class Classifier for the Detection of GAN Manipulated Multi-Spectral Satellite Images

引用

REMOTE SENSING 2024年第5期16卷 781-781页

作者： Abady, Lydia Dimitri, Giovanna Maria Barni, Mauro Univ Siena Dept Informat Engn & Math I-53100 Siena Italy

The current image generative models have achieved a remarkably realistic image quality, offering numerous academic and industrial applications. However, to ensure these models are used for benign purposes, it is essential to develop tools that definitively detect whether an image has been synthetically generated. Consequently, several detectors with excellent performance in computer vision applications have been developed. However, these detectors cannot be directly applied as they areto multi-spectral satellite images, necessitating the training of new models. While two-class classifiers generally achieve high detection accuracies, they struggle to generalize to image domains and generative architectures different from those encountered during training. In this paper, we propose a one-class classifier based on Vector Quantized variational autoencoder 2 (VQ-VAE 2) features to overcome the limitations of two-class classifiers. We start by highlighting the generalization problem faced by binary classifiers. This was demonstrated by training and testing an EfficientNet-B4 architecture on multiple multi-spectral datasets. We then illustrate that the VQ-VAE 2-based classifier, which was trained exclusively on pristine images, could detect images from different domains and generated by architectures not encountered during training. Finally, we conducted a head-to-head comparison between the two classifiers on the same generated datasets, emphasizing the superior generalization capabilities of the VQ-VAE 2-based detector, wherewe obtained a probability of detection at a 0.05 false alarm rate of 1 for the blue and red channels when using the VQ-VAE 2-based detector, and 0.72 when we used the EfficientNet-B4 classifier.

关键词： generative adversarial networks variational autoencoder EfficientNet detection Sentinel-2 remote sensing

来源：评论

学校读者我要写书评

暂无评论

Category-Stitch Learning for Union Domain Generalization

引用

ACM TRANSACTIONS ON MULTIMEDIA COMPUTING COMMUNICATIONS AND APPLICATIONS 2023年第1期19卷 25-25页

作者： Liu, Yajing Xiong, Zhiwei Li, Ya Lu, Yuning Tian, Xinmei Zha, Zheng-Jun Univ Sci & Technol China 443 Huangshan Rd Hefei 230027 Peoples R China iFLYTEK Res 666 Wangjiang West Rd Hefei 230088 Peoples R China

Domain generalization aims at generalizing the network trained on multiple domains to unknown but related domains. Under the assumption that different domains share the same classes, previous works can build relationships across domains. However, in realistic scenarios, the change of domains is always followed by the change of categories, which raises a difficulty for collecting sufficient aligned categories across domains. Bearing this in mind, this article introduces union domain generalization (UDG) as a new domain generalization scenario, in which the label space varies across domains, and the categories in unknown domains belong to the union of all given domain categories. The absence of categories in given domains is the main obstacle to aligning different domain distributions and obtaining domain-invariant information. To address this problem, we propose category-stitch learning (CSL), which aims at jointly learning the domain-invariant information and completing missing categories in all domains through an improved variational autoencoder and generators. The domain-invariant information extraction and sample generation cross-promote each other to better generalizability. Additionally, we decouple category and domain information and propose explicitly regularizing the semantic information by the classification loss with transferred samples. Thus our method can breakthrough the category limit and generate samples of missing categories in each domain. Extensive experiments and visualizations are conducted on MNIST, VLCS, PACS, Office-Home, and DomainNet datasets to demonstrate the effectiveness of our proposed method.

关键词： Domain generalization variational autoencoder generator

来源：评论

学校读者我要写书评

暂无评论

Stochastic variational inference for probabilistic optimal power flows

引用

ELECTRIC POWER SYSTEMS RESEARCH 2021年 200卷 107465-107465页

作者： Loschenbrand, Markus Sintef Energy Res Sem Saelands Vei 11 N-7034 Trondheim Norway

This paper applies a generative deep learning model, namely a variational autoencoder, on probabilistic optimal power flows. The model utilizes Gaussian approximations in order to adequately represent the distributions of the results of a system under uncertainty. These approximations are realized by applying several techniques from Bayesian deep learning, among them most notably Stochastic variational Inference. Using the reparameterization trick and batch sampling, the proposed model allows for the training a probabilistic optimal power flow similar to a possibilistic process. The results are shown by application of a reformulation of the Kullback-Leibler divergence, a distance measure of distributions. Not only is the resulting model simple in its appearance, it also shows to perform well and accurate. Furthermore, the paper also explores potential pathways for future research and gives insights for practitioners using such or similar generative models.

关键词： Probabilistic optimal power flow Neural networks Generative model variational autoencoder Bayesian statistics

来源：评论

学校读者我要写书评

暂无评论

Semi-supervised face aging and rejuvenating

引用

JOURNAL OF ELECTRONIC IMAGING 2021年第2期30卷 023003-023003页

作者： Ma, Wanyue Zhou, Yuan He, Jun Nanjing Univ Informat Sci & Technol Sch Elect & Informat Engn Nanjing Peoples R China Nanjing Univ Informat Sci & Technol Sch Artificial Intelligence Nanjing Peoples R China

Face aging and rejuvenating aim to generate an individual face with aging and rejuvenating effect while retaining identity information. We can analyze a given face image to estimate a past look or predict a future look of the person. The research on face aging and rejuvenating has important application value in the fields of cross-age recognition,1 public security, and entertainment, for example, changing the appearance of actors at different ages in a movie or finding missing persons in forensic applications. Although this area has attracted much attention of the researchers, there are still many challenges, especially in lack of accurate and sufficient dataset, low aging effect, and bad identity preservation. Previous face aging and rejuvenating methods are split into two main categories: physical model-based methods2,3 and prototype-based methods.4-6 The physical model-based methods describe the alteration in muscle, wrinkle, skin, etc., which can get a good result but suffer from complex modeling. The prototype-based methods try to learn the transformation between different age groups. Due to the development of generative adversarial network (GAN),7 state-of-theart methods8-10 that use the technology of deep learning show impressive success in this field. Face aging and rejuvenating work effectively in public security criminal investigation, cross-age recognition, and entertainment. However, three main problems still exist: the lack of accurate and sufficient dataset, low aging effect, and poor preservation of personal information. We propose a semi-supervised face aging and rejuvenating method for face aging and rejuvenating. In particular, a conditional encoder is utilized to map an input face into a latent vector, which is used by the generator network with age conditions to produce a new face. The latent vector preserves identity information, whereas the age label controls face aging or rejuvenating. To make generated features closer to prior features, the d

关键词： face aging and rejuvenating variational autoencoder feature embedding model adversarial training

来源：评论

学校读者我要写书评

暂无评论

Inverse design of dual-phase steel microstructures using generative machine learning model and Bayesian optimization

引用

INTERNATIONAL JOURNAL OF PLASTICITY 2023年 171卷

作者： Kusampudi, Navyanth Diehl, Martin Max Planck Inst Eisenforsch GmbH Max Planck Str 1 D-40237 Dusseldorf Germany Katholieke Univ Leuven Dept Mat Sci Kasteelpark Arenberg 44 B-3001 Leuven Belgium Katholieke Univ Leuven Dept Comp Sci Celestijnenlaan 200 A B-3001 Louvain Belgium

The design of optimal microstructures requires first, the identification of microstructural features that influence the material's properties and, then, a search for a combination of these features that give rise to desired properties. For microstructures with complex morphologies, where the number of features is large, deriving these structure-property relationships is a challenging task. To address this challenge, we propose a generative machine learning model that can automatically identify low-dimensional descriptors of microstructural features that can be used to establish structure-property relationships. Based on this model, we present an integrated, data-driven framework for microstructure characterization, reconstruction, and design that is applicable to heterogeneous materials with polycrystalline microstructures. The proposed method is evaluated on a case study of designing dual-phase steel microstructures created with the multi-level Voronoi tessellation method. To this end, we train a variational autoencoder to identify the descriptors from these synthetic dual-phase steel microstructures. Subsequently, we employ Bayesian optimization to search for the optimal combination of the descriptors and generate microstructures with specific yield stress and low susceptibility for damage initiation. The presented results show how microstructure descriptors, determined by the variational autoencoder model, act as design variables for an optimization algorithm that identifies microstructures with desired properties.

关键词： Crystal plasticity variational autoencoder Voronoi tessellation Random forest

来源：评论

学校读者我要写书评

暂无评论

Satellite Network Security Routing Technology Based on Deep Learning and Trust Management

引用

SENSORS 2023年第20期23卷 8474-8474页

作者： Liu, Zhiguo Rong, Junlin Jiang, Yingru Zhang, Luxi Dalian Univ Commun & Network Lab Dalian 116622 Peoples R China

The conventional trust model employed in satellite network security routing algorithms exhibits limited accuracy in detecting malicious nodes and lacks adaptability when confronted with unknown attacks. To address this challenge, this paper introduces a secure satellite network routing technology founded on deep learning and trust management. The approach embraces the concept of distributed trust management, resulting in all satellite nodes in this paper being equipped with trust management and anomaly detection modules for assessing the security of neighboring nodes. In a more detailed breakdown, this technology commences by preprocessing the communication behavior of satellite network nodes using D-S evidence theory, effectively mitigating interference factors encountered during the training of VAE modules. Following this preprocessing step, the trust vector, which has undergone prior processing, is input into the VAE module. Once the VAE module's training is completed, the satellite network can assess safety factors by employing the safety module during the collection of trust evidence. Ultimately, these security factors can be integrated with the pheromone component within the ant colony algorithm to guide the ants in discovering pathways. Simulation results substantiate that the proposed satellite network secure routing algorithm effectively counters the impact of malicious nodes on data transmission within the network. When compared to the traditional trust management model of satellite network secure routing algorithms, the algorithm demonstrates enhancements in average end-to-end delay, packet loss rate, and throughput.

关键词： trust management D-S evidence theory variational autoencoder secure routing

来源：评论

学校读者我要写书评

暂无评论

PCovNet: A presymptomatic COVID-19 detection framework using deep learning model using wearables data

引用

COMPUTERS IN BIOLOGY AND MEDICINE 2022年 147卷 105682-105682页

作者： Abir, Farhan Fuad Alyafei, Khalid Chowdhury, Muhammad E. H. Khandakar, Amith Ahmed, Rashid Hossain, Muhammad Maqsud Mahmud, Sakib Rahman, Ashiqur Abbas, Tareq O. Zughaier, Susu M. Naji, Khalid Kamal Univ Dhaka Dept Elect & Elect Engn Dhaka 1000 Bangladesh Qatar Univ Coll Engn Dept Mech & Ind Engn Doha 2713 Qatar Qatar Univ Dept Elect Engn Doha 2713 Qatar Qatar Univ Biomed Res Ctr Doha 2713 Qatar North South Univ NSU Genome Res Inst NGRI Dhaka 1229 Bangladesh Tohoku Univ Inst Multidisciplinary Res Adv Mat Sendai Japan Surg Dept Urol Div Sidra Med Doha 26999 Qatar Qatar Univ Coll Med Dept Basic Med Sci QU Hlth Doha 2713 Qatar Qatar Univ Coll Engn Doha 2713 Qatar

While the advanced diagnostic tools and healthcare management protocols have been struggling to contain the COVID-19 pandemic, the spread of the contagious viral pathogen before the symptom onset acted as the Achilles' heel. Although reverse transcription-polymerase chain reaction (RT-PCR) has been widely used for COVID-19 diagnosis, they are hardly administered before any visible symptom, which provokes rapid transmission. This study proposes PCovNet, a Long Short-term Memory variational autoencoder (LSTM-VAE)-based anomaly detection framework, to detect COVID-19 infection in the presymptomatic stage from the Resting Heart Rate (RHR) derived from the wearable devices, i.e., smartwatch or fitness tracker. The framework was trained and evaluated in two configurations on a publicly available wearable device dataset consisting of 25 COVID-positive individuals in the span of four months including their COVID-19 infection phase. The first configuration of the framework detected RHR abnormality with average Precision, Recall, and F-beta scores of 0.946, 0.234, and 0.918, respectively. However, the second configuration detected aberrant RHR in 100% of the subjects (25 out of 25) during the infectious period. Moreover, 80% of the subjects (20 out of 25) were detected during the presymptomatic stage. These findings prove the feasibility of using wearable devices with such a deep learning framework as a secondary diagnosis tool to circumvent the presymptomatic COVID-19 detection problem.

关键词： Presymptomatic COVID-19 Smartwatch Resting heart rate Anomaly detection Long short -term memory variational autoencoder

来源：评论

学校读者我要写书评

暂无评论

VAPER: A deep learning model for explainable probabilistic regression

引用

JOURNAL OF COMPUTATIONAL SCIENCE 2022年第0期63卷

作者： Jung, Seungwon Noh, Yoona Moon, Jaeuk Hwang, Eenjun Korea Univ Sch Elect Engn Seoul 02841 South Korea

A probabilistic regression model provides decision-makers with the regression output along with its quantitative uncertainty for given input variables. Even though this uncertainty may help to avoid serious consequences such as misdiagnosis or blackout due to overconfidence in the output, it only provides a measure of the uncertainty of the output, and has a limitation in that it cannot explain the reasons for the output and its uncertainty. If they can be presented along with their reasons, more suitable alternatives to the output can be found. However, despite the development of artificial intelligence methods to explain machine learning models and their outputs, few probabilistic regression models with this functionality have been proposed. Therefore, in this paper, we propose a variational autoencoder-based model for explainable probabilistic regression, called VAPER. VAPER provides a parametric probability distribution of an output variable over input variables and interprets it using layer-wise relevance propagation to investigate the effect of each input variable. To evaluate the effectiveness of the pro-posed model, we performed extensive experiments using several datasets. The experimental results demonstrated that VAPER has competitive regression performance compared to existing models, even with effective explainability.

关键词： Probabilistic regression Explainable artificial intelligence Layer -wise relevance propagation variational autoencoder

来源：评论

学校读者我要写书评

暂无评论

Learning to balance the coherence and diversity of response generation in generation-based chatbots

引用

INTERNATIONAL JOURNAL OF ADVANCED ROBOTIC SYSTEMS 2020年第4期17卷

作者： Wang, Shuliang Li, Dapeng Geng, Jing Yang, Longxing Leng, Hongyong Beijing Inst Technol Sch Comp Sci & Technol 5 South St Beijing 100081 Peoples R China Beijing Inst Technol Acad E Govt Beijing Peoples R China Chinese Acad Sci Inst Comp Technol Beijing Peoples R China

Generating response with both coherence and diversity is a challenging task in generation-based chatbots. It is more difficult to improve the coherence and diversity of dialog generation at the same time in the response generation model. In this article, we propose an improved method that improves the coherence and diversity of dialog generation by changing the model to use gamma sampling and adding attention mechanism to the knowledge-guided conditional variational autoencoder. The experimental results demonstrate that our proposed method can significantly improve the coherence and diversity of knowledge-guided conditional variational autoencoder for response generation in generation-based chatbots at the same time.

关键词： variational autoencoder dialog system deep learning response generation chatbots

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：