检索结果-内蒙古大学图书馆

arXiv 2023年

作者： Chijiwa, Daiki NTT Computer and Data Science Laboratories NTT Corporation Japan

Training deep neural networks (DNNs) is computationally expensive, which is problematic especially when performing duplicated or similar training runs in model ensemble or fine-tuning pre-trained models, for example. Once we have trained one DNN on some dataset, we have its learning trajectory (i.e., a sequence of intermediate parameters during training) which may potentially contain useful information for learning the dataset. However, there has been no attempt to utilize such information of a given learning trajectory for another training. In this paper, we formulate the problem of "transferring" a given learning trajectory from one initial parameter to another one (named learning transfer problem) and derive the first algorithm to approximately solve it by matching gradients successively along the trajectory via permutation symmetry. We empirically show that the transferred parameters achieve non-trivial accuracy before any direct training, and can be trained significantly faster than training from scratch. Copyright © 2023, The Authors. All rights reserved.

关键词： Deep neural networks

来源：评论

学校读者我要写书评

暂无评论

OnDA-DETR: Online Domain Adaptation for Detection Transformers with Self-Training Framework

OnDA-DETR: Online Domain Adaptation for Detection Transforme...

引用

IEEE International Conference on Image Processing

作者： Satoshi Suzuki Taiga Yamane Naoki Makishima Keita Suzuki Atsushi Ando Ryo Masumura NTT Computer and Data Science Laboratories NTT Corporation Japan

This paper presents a novel method for online domain adaptation (OnDA) for DEtection TRansformer (DETR)-based object detection models called OnDA-DETR. OnDA is a domain adaptation paradigm that adapts a model trained on the source domain data to perform well on the target domain in an online manner during testing, using only the unlabeled test data from the target domain. Due to challenging and realistic problem settings, OnDA has garnered significant attention. However, OnDA methods for DETR-based models, which have demonstrated excellent performance in object detection research fields, had not been developed. OnDA-DETR is the first OnDA method specifically designed for DETR-based models. OnDA-DETR incorporates a self-training framework that generates pseudo-labels for the unlabeled target domain data. To effectively incorporate the self-training framework into DETR-based models, we leverage recall-aware pseudo-labeling and quality-aware training in OnDA-DETR. Experimental results indicate that OnDA-DETR improves the performance of the source-trained model by about 3.0 % points through OnDA.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Open-Set Recognition for Facial-Expression Recognition

Open-Set Recognition for Facial-Expression Recognition

引用

IEEE International Conference on Image Processing

作者： Mihiro Uchida Shota Orihashi Akihiko Takashima Yoshihiro Yamazaki Ryo Masumura NTT Computer and Data Science Laboratories NTT Corporation Japan

We address distinguishing whether an input is a facial image by learning only a facial-expression recognition (FER) dataset. To avoid misclassification in FER, it is necessary to distinguish whether the input is a facial image. Unfortunately, collecting exhaustive non-face images is costly. Therefore, distinguishing whether the input is a facial image by learning only an FER dataset is important. A representative method for this task is learning reconstruction of only facial images and determining high-error samples between input images and reconstructed images as non-face images. However, reconstruction is difficult on facial images because such images contain detailed features. Our key idea to tackle the task without reconstruction is assuming that facial images will match several emotions, whereas non-face images will not match any emotion. Therefore, we propose a method for training a discriminator that determines whether the inputs and emotions match using counter-factual pairs in an FER dataset. A metric for the task is then obtained by taking into account each emotion in the posterior probability that inputs and emotions match, estimated by the discriminator. Experiments on the RAF-DB dataset vs. the Stanford Dogs dataset and AffectNet datasets showed the effectiveness of our method.

关键词：

来源：评论

学校读者我要写书评

暂无评论

META-LEARNING TO CALIBRATE GAUSSIAN PROCESSES WITH DEEP KERNELS FOR REGRESSION UNCERTAINTY ESTIMATION A PREPRINT

arXiv

引用

arXiv 2023年

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

Although Gaussian processes (GPs) with deep kernels have been succesfully used for meta-learning in regression tasks, its uncertainty estimation performance can be poor. We propose a meta-learning method for calibrating deep kernel GPs for improving regression uncertainty estimation performance with a limited number of training data. The proposed method meta-learns how to calibrate uncertainty using data from various tasks by minimizing the test expected calibration error, and uses the knowledge for unseen tasks. We design our model such that the adaptation and calibration for each task can be performed without iterative procedures, which enables effective meta-learning. In particular, a taskspecific uncalibrated output distribution is modeled by a GP with a task-shared encoder network, and it is transformed to a calibrated one using a cumulative density function of a task-specific Gaussian mixture model (GMM). By integrating the GP and GMM into our neural network-based model, we can meta-learn model parameters in an end-to-end fashion. Our experiments demonstrate that the proposed method improves uncertainty estimation performance while keeping high regression performance compared with the existing methods using real-world datasets in few-shot settings. Copyright © 2023, The Authors. All rights reserved.

关键词： Calibration

来源：评论

学校读者我要写书评

暂无评论

Dispute resolution in accessible voting systems: The design and use of audiotegrity

引用

4th International Conference on E-Voting and Identity, Vote-ID 2013

作者： Kaczmarek, Tyler Wittrock, John Carback, Richard Florescu, Alex Rubio, Jan Runyan, Noel Vora, Poorvi L. Zagórski, Filip Department of Computer Science George Washington University United States Network and Information Concepts Group Charles Stark Draper Laboratories United States Personal Data Systems United States Institute of Mathematics and Computer Science Wroclaw University of Technology Poland

ISBN: (纸本)9783642391842

We describe in detail dispute resolution problems with cryptographic voting systems that do not produce a paper record of the unencrypted vote. With these in mind, we describe the design and use of Audiotegrity - a cryptographic voting protocol and corresponding voting system with some of the accessibility benefits of fully-electronic voting systems and some of the dispute resolution properties of paper-ballot-based systems. We also describe subtle issues with coercion-resistance if accessible systems are not well-designed. Audiotegrity was designed in response to a request by Takoma Park election officials, tested in a public test organized by the city in June 2011, and used in its municipal election in November 2011. We are not aware of any other precinct-based end-to-end independently-verifiable election for public office where the protocol enabled participation by voters with visual disabilities. © 2013 Springer-Verlag Berlin Heidelberg.

关键词： Cryptography

来源：评论

学校读者我要写书评

暂无评论

Adversarial Finetuning with Latent Representation Constraint to Mitigate Accuracy-Robustness Tradeoff

Adversarial Finetuning with Latent Representation Constraint...

引用

International Conference on computer Vision (ICCV)

作者： Satoshi Suzuki Shin’ya Yamaguchi Shoichiro Takeda Sekitoshi Kanai Naoki Makishima Atsushi Ando Ryo Masumura NTT Computer and Data Science Laboratories Kyoto University NTT Human Informatics Laboratories

This paper addresses the tradeoff between standard accuracy on clean examples and robustness against adversarial examples in deep neural networks (DNNs). Although adversarial training (AT) improves robustness, it degrades the standard accuracy, thus yielding the tradeoff. To mitigate this tradeoff, we propose a novel AT method called ARREST, which comprises three components: (i) adversarial finetuning (AFT), (ii) representation-guided knowledge distillation (RGKD), and (iii) noisy replay (NR). AFT trains a DNN on adversarial examples by initializing its parameters with a DNN that is standardly pretrained on clean examples. RGKD and NR respectively entail a regularization term and an algorithm to preserve latent representations of clean examples during AFT. RGKD penalizes the distance between the representations of the standardly pretrained and AFT DNNs. NR switches input adversarial examples to nonadversarial ones when the representation changes significantly during AFT. By combining these components, ARREST achieves both high standard accuracy and robustness. Experimental results demonstrate that ARREST mitigates the tradeoff more effectively than previous AT-based methods do.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Sharing knowledge for meta-learning with feature descriptions 22

Sharing knowledge for meta-learning with feature description...

引用

Proceedings of the 36th International Conference on Neural Information Processing Systems

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

ISBN: (纸本)9781713871088

Language is an important tool for humans to share knowledge. We propose a meta-learning method that shares knowledge across supervised learning tasks using feature descriptions written in natural language, which have not been used in the existing meta-learning methods. The proposed method improves the predictive performance on unseen tasks with a limited number of labeled data by meta-learning from various tasks. With the feature descriptions, we can find relationships across tasks even when their feature spaces are different. The feature descriptions are encoded using a language model pretrained with a large corpus, which enables us to incorporate human knowledge stored in the corpus into meta-learning. In our experiments, we demonstrate that the proposed method achieves better predictive performance than the existing meta-learning methods using a wide variety of real-world datasets provided by the statistical office of the EU and Japan.

关键词：

来源：评论

学校读者我要写书评

暂无评论

A Security Verification Framework of Cryptographic Protocols Using Machine Learning

arXiv

引用

arXiv 2023年

作者： Ohno, Kentaro Nakabayashi, Misato NTT Computer & Data Science Laboratories Japan NTT Social Informatics Laboratories Japan

We propose a security verification framework for cryptographic protocols using machine learning. In recent years, as cryptographic protocols have become more complex, research on automatic verification techniques has been focused on. The main technique is formal verification. However, the formal verification has two problems: it requires a large amount of computational time and does not guarantee decidability. We propose a method that allows security verification with computational time on the order of linear with respect to the size of the protocol using machine learning. In training machine learning models for security verification of cryptographic protocols, a sufficient amount of data, i.e., a set of protocol data with security labels, is difficult to collect from academic papers and other sources. To overcome this issue, we propose a way to create arbitrarily large datasets by automatically generating random protocols and assigning security labels to them using formal verification tools. Furthermore, to exploit structural features of protocols, we construct a neural network that processes a protocol along its series and tree structures. We evaluate the proposed method by applying it to verification of practical cryptographic protocols. © 2023, CC BY.

关键词： Machine learning

来源：评论

学校读者我要写书评

暂无评论

Robust Sparse Approximations for Stochastic Dynamical Systems

引用

IFAC-PapersOnLine 2017年第1期50卷 14010-14015页

作者： Quinn, Christopher J. Pinar, Ali Gao, Jing Su, Lu School of Industrial Engineering Purdue University West LafayetteIN United States Data Sciences & Cyber Anal. Dept. Sandia National Laboratories LivermoreCA United States Dept. of Computer Science and Engineering University at Buffalo BuffaloNY United States

Inferring the exact topology of the interactions in a large, stochastic dynamical system from time-series data can often be prohibitive computationally and statistically without strong side information. One alternative is to seek approximations of the system topology that nonetheless describe the data well. In recent works, algorithms were proposed to identify sparse approximations which are optimal in terms of Kullback-Leibler divergence. Those algorithms relied on point estimates of statistics from the data. In this work, we investigate the more practical setting where point estimates are not reliable. We propose an algorithm to identify sparse, connected approximations that are robust to estimation error. © 2017

关键词： Approximation algorithms Dynamical systems Identification (control systems) Nonlinear systems Stochastic systems Time series Topology Errors in variables Model reduction Nonparametric methods Robust estimation Time series modeling

来源：评论

学校读者我要写书评

暂无评论

Adversarial Finetuning with Latent Representation Constraint to Mitigate Accuracy-Robustness Tradeoff

arXiv

引用

arXiv 2023年

作者： Suzuki, Satoshi Yamaguchi, Shinya Takeda, Shoichiro Kanai, Sekitoshi Makishima, Naoki Ando, Atsushi Masumura, Ryo NTT Computer and Data Science Laboratories Kyoto University Japan NTT Human Informatics Laboratories

关键词： Deep neural networks

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：