检索结果-内蒙古大学图书馆

arXiv 2023年

作者： Ida, Yasutoshi Kanai, Sekitoshi Adachi, Kazuki Kumagai, Atsutoshi Fujiwara, Yasuhiro NTT Computer and Data Science Laboratories Japan NTT Communication Science Laboratories Japan

Regularized discrete optimal transport (OT) is a powerful tool to measure the distance between two discrete distributions that have been constructed from data samples on two different domains. While it has a wide range of applications in machine learning, in some cases the sampled data from only one of the domains will have class labels such as unsupervised domain adaptation. In this kind of problem setting, a group-sparse regularizer is frequently leveraged as a regularization term to handle class labels. In particular, it can preserve the label structure on the data samples by corresponding the data samples with the same class label to one group-sparse regularization term. As a result, we can measure the distance while utilizing label information by solving the regularized optimization problem with gradient-based algorithms. However, the gradient computation is expensive when the number of classes or data samples is large because the number of regularization terms and their respective sizes also turn out to be large. This paper proposes fast discrete OT with group-sparse regularizers. Our method is based on two ideas. The first is to safely skip the computations of the gradients that must be zero. The second is to efficiently extract the gradients that are expected to be nonzero. Our method is guaranteed to return the same value of the objective function as that of the original method. Experiments show that our method is up to 8.6 times faster than the original method without degrading accuracy. Copyright © 2023, The Authors. All rights reserved.

关键词： Machine learning

来源：评论

学校读者我要写书评

暂无评论

DEEP QUANTIGRAPHIC IMAGE ENHANCEMENT VIA COMPARAMETRIC EQUATIONS

arXiv

引用

arXiv 2023年

作者： Wu, Xiaomeng Sun, Yongqing Kimura, Akisato Communication Science Laboratories NTT Corporation Computer and Data Science Laboratories NTT Corporation

Most recent methods of deep image enhancement can be generally classified into two types: decompose-and-enhance and illumination estimation-centric. The former is usually less efficient, and the latter is constrained by a strong assumption regarding image reflectance as the desired enhancement result. To alleviate this constraint while retaining high efficiency, we propose a novel trainable module that diversifies the conversion from the low-light image and illumination map to the enhanced image. It formulates image enhancement as a comparametric equation parameterized by a camera response function and an exposure compensation ratio. By incorporating this module in an illumination estimation-centric DNN, our method improves the flexibility of deep image enhancement, limits the computational burden to illumination estimation, and allows for fully unsupervised learning adaptable to the diverse demands of different tasks. Copyright © 2023, The Authors. All rights reserved.

关键词： Image enhancement

来源：评论

学校读者我要写书评

暂无评论

Deep Quantigraphic Image Enhancement via Comparametric Equations

Deep Quantigraphic Image Enhancement via Comparametric Equat...

引用

International Conference on Acoustics, Speech, and Signal Processing (ICASSP)

作者： Xiaomeng Wu Yongqing Sun Akisato Kimura Communication Science Laboratories NTT Corporation Computer and Data Science Laboratories NTT Corporation

关键词： Reflectivity Semantic segmentation Lighting Object detection Speech enhancement Signal processing Mathematical models

来源：评论

学校读者我要写书评

暂无评论

META-LEARNING OF SEMI-SUPERVISED LEARNING FROM TASKS WITH HETEROGENEOUS ATTRIBUTE SPACES

arXiv

引用

arXiv 2023年

作者： Iwata, Tomoharu Kumagai, Atsutoshi NTT Communication Science Laboratories Japan NTT Computer and Data Science Laboratories Japan

We propose a meta-learning method for semi-supervised learning that learns from multiple tasks with heterogeneous attribute spaces. The existing semi-supervised meta-learning methods assume that all tasks share the same attribute space, which prevents us from learning with a wide variety of tasks. With the proposed method, the expected test performance on tasks with a small amount of labeled data is improved with unlabeled data as well as data in various tasks, where the attribute spaces are different among tasks. The proposed method embeds labeled and unlabeled data simultaneously in a task-specific space using a neural network, and the unlabeled data's labels are estimated by adapting classification or regression models in the embedding space. For the neural network, we develop variable-feature self-attention layers, which enable us to find embeddings of data with different attribute spaces with a single neural network by considering interactions among examples, attributes, and labels. Our experiments on classification and regression datasets with heterogeneous attribute spaces demonstrate that our proposed method outperforms the existing meta-learning and semi-supervised learning methods. Copyright © 2023, The Authors. All rights reserved.

关键词： Embeddings

来源：评论

学校读者我要写书评

暂无评论

Meta-learning for Positive-unlabeled Classification

arXiv

引用

arXiv 2024年

作者： Kumagai, Atsutoshi Iwata, Tomoharu Fujiwara, Yasuhiro NTT Computer and Data Science Laboratories Japan NTT Communication Science Laboratories Japan

We propose a meta-learning method for positive and unlabeled (PU) classification, which improves the performance of binary classifiers obtained from only PU data in unseen target tasks. PU learning is an important problem since PU data naturally arise in real-world applications such as outlier detection and information retrieval. Existing PU learning methods require many PU data, but sufficient data are often unavailable in practice. The proposed method minimizes the test classification risk after the model is adapted to PU data by using related tasks that consist of positive, negative, and unlabeled data. We formulate the adaptation as an estimation problem of the Bayes optimal classifier, which is an optimal classifier to minimize the classification risk. The proposed method embeds each instance into a task-specific space using neural networks. With the embedded PU data, the Bayes optimal classifier is estimated through density-ratio estimation of PU densities, whose solution is obtained as a closed-form solution. The closed-form solution enables us to efficiently and effectively minimize the test classification risk. We empirically show that the proposed method outperforms existing methods with one synthetic and three real-world datasets. Copyright © 2024, The Authors. All rights reserved.

关键词： Risk perception

来源：评论

学校读者我要写书评

暂无评论

Text-to-Text Pre-Training with Paraphrasing for Improving Transformer-Based Image Captioning

Text-to-Text Pre-Training with Paraphrasing for Improving Tr...

引用

European Signal Processing Conference (EUSIPCO)

作者： Ryo Masumura Naoki Makishima Mana Ihori Akihiko Takashima Tomohiro Tanaka Shota Orihashi NTT Computer & Data Science Laboratories NTT Corporation

In this paper, we propose a novel training method for the transformer encoder-decoder based image captioning, which directly generates a captioning text from an input image. In general, many image- to- text paired datasets need to be prepared for robust image captioning, but such datasets cannot be collected in practical cases. Our key idea for mitigating the data preparation cost is to utilize text-to-text paraphrasing modeling, i.e., a task to convert an input text into different expressions without changing the meaning. In fact, paraphrasing deals with a similar transformation task to image captioning even though paraphrasing tasks have to handle texts instead of images. In our proposed method, an encoder-decoder network trained via the paraphrasing task is directly leveraged for image captioning. Thus, an encoder-decoder network pre-trained by a text-to-text transformation task is transferred into an image-to-text transformation task even though a different modal must be handled in the encoder network. Our experiments using the MS COCO caption datasets demonstrate the effectiveness of the proposed method.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Discovering Implicit Operational Knowledge by Identifying Business Processes that Involve Multiple Organizational Entities

Discovering Implicit Operational Knowledge by Identifying Bu...

引用

IEEE Annual International computer Software and Applications Conference (COMPSAC)

作者： Shinobu Saito Yukako Iimura NTT Computer and Data Science Laboratories Tokyo Japan

ISBN: (数字)9798350376968

ISBN: (纸本)9798350376975

One of the success factors of Business process outsourcing (BPO) is a comprehensive and in-depth understanding of the business processes outsourced. However, such business processes are often undocumented, and discovering them is difficult and time-consuming for BPO service providers. Previously, we introduced an approach for business process discovery that uses swim lanes to recognize that different parts of the process may be performed by different parts of an organization. It generates the business process from an event log and user information extracted from an existing system. Herein, this paper examines whether the approach aids engineers and consultants in the providers who need to investigate business processes of organizations (i.e., their customers on which they do not have sufficient knowledge) discovering the implicit operational knowledge of the target business processes (e.g., undocumented local rules). To do so, we survey an industrial workflow system from which we collected data about 2,000 events and 269 users for a two-year period of the system's operation. We conducted a study on the case by means of document evaluation and expert interviews. The study suggested that the output of the approach is a valuable process visualization for identifying knowledge that is not documented nor recognized by even experts in organizations.

关键词： Knowledge engineering Surveys data visualization Organizations Manuals Software Outsourcing

来源：评论

学校读者我要写书评

暂无评论

Covariance-Aware Feature Alignment with Pre-Computed Source Statistics for Test-Time Adaptation to Multiple Image Corruptions

Covariance-Aware Feature Alignment with Pre-Computed Source ...

引用

IEEE International Conference on Image Processing

作者： Kazuki Adachi Shin’Ya Yamaguchi Atsutoshi Kumagai NTT Computer and Data Science Laboratories Kyoto University

Real-world image recognition systems often face corrupted input images, which cause distribution shifts and degrade the performance of models. These systems often use a single prediction model in a central server and process images sent from various environments, such as cameras distributed in cities or cars. Such single models face images corrupted in heterogeneous ways in test time. Thus, they require to instantly adapt to the multiple corruptions during testing rather than being re-trained at a high cost. Test-time adaptation (TTA), which aims to adapt models without accessing the training dataset, is one of the settings that can address this problem. Existing TTA methods indeed work well on a single corruption. However, the adaptation ability is limited when multiple types of corruption occur, which is more realistic. We hypothesize this is because the distribution shift is more complicated, and the adaptation becomes more difficult in case of multiple corruptions. In fact, we experimentally found that a larger distribution gap remains after TTA. To address the distribution gap during testing, we propose a novel TTA method named Covariance-Aware Feature alignment (CAFe). We empirically show that CAFe outperforms prior TTA methods on image corruptions, including multiple types of corruptions.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Towards N-version Quantum Software Systems for Reliable Classical-Quantum Computing

Towards N-version Quantum Software Systems for Reliable Clas...

引用

IEEE International Conference on Software Reliability Engineering Workshops (ISSRE Wksp)

作者： Shinobu Saito Suguru Endo Yasunari Suzuki NTT Computer and Data Science Laboratories Tokyo Japan

ISBN: (数字)9798350367041

ISBN: (纸本)9798350367058

While quantum computers have attracted much attention, dealing with computational errors due to noise effects caused by the interaction between quantum hardware and the external environment is a significant challenge. In this paper, we propose an approach to apply N-version programming (NVP) to quantum software to improve the reliability of the entire quantum software system. First, we define architecture patterns for N-version quantum software systems (NVQS) based on a combination of quantum libraries and devices. Next, given that the output of the quantum software system is a probability distribution, we came up with an evaluation strategy inspired by the concept of NVP for clustering and selecting multiple probability distributions output from NVQS. Finally, we outline our future experimental plan.

关键词： Quantum computing Conferences Noise Programming Software systems Reliability engineering Probability distribution Libraries Hardware Software reliability

来源：评论

学校读者我要写书评

暂无评论

Coding and Debugging by Separating Secret Code Toward Secure Remote Development 23

Coding and Debugging by Separating Secret Code Toward Secure...

引用

Proceedings of the 38th IEEE/ACM International Conference on Automated Software Engineering

作者： Shinobu Saito NTT Computer and Data Science Laboratories Tokyo Japan

ISBN: (纸本)9798350329964

It is a higher priority for organizations to keep their source code secured. When a certain specific code includes a secret such as intellectual property, they need to pay special attention to prevent the secret code from leaking outside. On the other hand, sometimes code leaks comes from acts by inside programmers. This industrial paper proposes a MORDEn (Micro Organized Remote Development Environment) toward preventing code leaks. MORDEn enables programmers capable of coding and debugging by physically separating secret code from their client. We also introduce a showcase that demonstrates the feasibility of MORDEn from a case study project using it.

关键词： remote development environment

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：