检索结果-内蒙古大学图书馆

40th International Conference on Machine Learning, ICML 2023

作者： Han, Hyeongrok Siwon, Kim Choi, Hyun-Soo Yoon, Sungroh Department of Electrical and Computer Engineering Seoul National University Seoul Korea Republic of Department of Computer Science and Engineering Seoul National University of Science and Technology Seoul Korea Republic of ZIOVISION Inc. Chuncheon Korea Republic of Interdisciplinary Program in Artificial Intelligence Seoul National University Seoul Korea Republic of

Several recent studies have elucidated why knowledge distillation (KD) improves model performance. However, few have researched the other advantages of KD in addition to its improving model performance. In this study, we have attempted to show that KD enhances the interpretability as well as the accuracy of models. We measured the number of concept detectors identified in network dissection for a quantitative comparison of model interpretability. We attributed the improvement in interpretability to the class-similarity information transferred from the teacher to student models. First, we confirmed the transfer of class-similarity information from the teacher to student model via logit distillation. Then, we analyzed how class-similarity information affects model interpretability in terms of its presence or absence and degree of similarity information. We conducted various quantitative and qualitative experiments and examined the results on different datasets, different KD methods, and according to different measures of interpretability. Our research showed that KD models by large models could be used more reliably in various fields. The code is available at https://***/Rok07/KD_***. © 2023 Proceedings of Machine Learning Research. All rights reserved.

关键词： Distillation

来源：评论

学校读者我要写书评

暂无评论

Optimal first-order algorithms as a function of inequalities

The Journal of Machine Learning Research

引用

The Journal of Machine Learning Research 2024年第1期25卷 2557-2625页

作者： Chanwoo Park Ernest K. Ryu Department of Electrical Engineering and Computer Science Massachusetts Institute of Technology Massachusetts Department of Mathematical Sciences Interdisciplinary Program in Artificial Intelligence Seoul National University Seoul Korea

In this work, we present a novel algorithm design methodology that finds the optimal algorithm as a function of inequalities. Specifically, we restrict convergence analyses of algorithms to use a prespecified subset of inequalities, rather than utilizing all true inequalities, and find the optimal algorithm subject to this restriction. This methodology allows us to design algorithms with certain desired characteristics. As concrete demonstrations of this methodology, we find new state-of-the-art accelerated first-order gradient methods using randomized coordinate updates and backtracking line searches.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Vision-Based Drug Classification System Using Transfer Learning Approach

Vision-Based Drug Classification System Using Transfer Learn...

引用

International Conference on Business and Industrial Research (ICBIR)

作者： Patpon Laohakijvitoon Sivapong Nilwong Master of Engineering Program in Engineering Technology Thai-Nichi Institute of Technology Bangkok Thailand Department of Computer Engineering and Artificial Intelligence Thai-Nichi Institute of Technology Bangkok Thailand

ISBN: (数字)9798350383027

ISBN: (纸本)9798350383034

Dispensing generic drugs instead of original drugs from pharmacies may cause adverse drug events to patients. It is difficult to separate between generic drugs and originals due to their similarities, except for imprints on the tablets. In this paper, a vision-based medicine tablets classification system using Convolutional Neural Networks (CNN) with a transfer learning approach is proposed. The proposed classification system aims to helps its user distinguish between the original drugs and generic drugs based on imprints on the medicine tablets. Multiple CNN models are created and tested as the classifier for the drug classification system. Three well-known CNN models are chosen as base models for creating CNNs with the transfer learning, including VGG16, Inception-V3, and ResNet50-V2. The developed CNN models are tested with images of medicine tablet taken from smartphones. Results from the experiments are evaluated through accuracies, precisions, recalls, and F-1 scores. Experimental results show satisfying performances of the proposed system in classifying original drugs and generic drugs using visual information.

关键词： Drugs Visualization Image processing Transfer learning Data preprocessing Medical services Mobile applications Convolutional neural networks Smart phones Biomedical imaging

来源：评论

学校读者我要写书评

暂无评论

STEIN LATENT OPTIMIZATION FOR GENERATIVE ADVERSARIAL NETWORKS 10

STEIN LATENT OPTIMIZATION FOR GENERATIVE ADVERSARIAL NETWORK...

引用

10th International Conference on Learning Representations, ICLR 2022

作者： Hwang, Uiwon Kim, Heeseung Jung, Dahuin Jang, Hyemi Lee, Hyungyu Yoon, Sungroh Department of Electrical and Computer Engineering AIIS ASRI INMC ISRC NSI and Interdisciplinary Program in Artificial Intelligence Seoul National University Seoul08826 Korea Republic of

Generative adversarial networks (GANs) with clustered latent spaces can perform conditional generation in a completely unsupervised manner. In the real world, the salient attributes of unlabeled data can be imbalanced. However, most of existing unsupervised conditional GANs cannot cluster attributes of these data in their latent spaces properly because they assume uniform distributions of the attributes. To address this problem, we theoretically derive Stein latent optimization that provides reparameterizable gradient estimations of the latent distribution parameters assuming a Gaussian mixture prior in a continuous latent space. Structurally, we introduce an encoder network and novel unsupervised conditional contrastive loss to ensure that data generated from a single mixture component represent a single attribute. We confirm that the proposed method, named Stein Latent Optimization for GANs (SLOGAN), successfully learns balanced or imbalanced attributes and achieves state-of-the-art unsupervised conditional generation performance even in the absence of attribute information (e.g., the imbalance ratio). Moreover, we demonstrate that the attributes to be learned can be manipulated using a small amount of probe data. © 2022 ICLR 2022 - 10th International Conference on Learning Representationss. All rights reserved.

关键词： Generative adversarial networks

来源：评论

学校读者我要写书评

暂无评论

3D geometric shape assembly via efficient point cloud matching 24

3D geometric shape assembly via efficient point cloud matchi...

引用

Proceedings of the 41st International Conference on Machine Learning

作者： Nahyuk Lee Juhong Min Junha Lee Seungwook Kim Kanghee Lee Jaesik Park Minsu Cho Department of Computer Science and Engineering POSTECH Pohang Korea Graduate School of Artificial Intelligence POSTECH Pohang Korea Department of Computer Science and Engineering Seoul National University Seoul Korea Department of Computer Science and Engineering Seoul National University Seoul Korea and Interdisciplinary Program in Artificial Intelligence Seoul National University Seoul Korea Department of Computer Science and Engineering POSTECH Pohang Korea and Graduate School of Artificial Intelligence POSTECH Pohang Korea

Learning to assemble geometric shapes into a larger target structure is a pivotal task in various practical applications. In this work, we tackle this problem by establishing local correspondences between point clouds of part shapes in both coarse- and fine-levels. To this end, we introduce Proxy Match Transform (PMT), an approximate high-order feature transform layer that enables reliable matching between mating surfaces of parts while incurring low costs in memory and compute. Building upon PMT, we introduce a new framework, dubbed Proxy Match TransformeR (PMTR), for the geometric assembly task. We evaluate the proposed PMTR on the large-scale 3D geometric shape assembly benchmark dataset of Breaking Bad and demonstrate its superior performance and efficiency compared to state-of-the-art methods. Project page: https://***/pmtr.

关键词：

来源：评论

学校读者我要写书评

暂无评论

An Overview of Facial Micro-Expression Analysis: Data, Methodology and Challenge

引用

IEEE Transactions on Affective Computing 2023年第3期14卷 1857-1875页

作者： Xie, Hong-Xia Lo, Ling Shuai, Hong-Han Cheng, Wen-Huang National Yang Ming Chiao Tung Univresity Institute of Electronics Hsinchu300093 Taiwan National Yang Ming Chiao Tung Univresity Department of Electrical and Computer Engineering Hsinchu300093 Taiwan National Chung Hsing University Artificial Intelligence and Data Science Program Taichung40227 Taiwan

Facial micro-expressions indicate brief and subtle facial movements that appear during emotional communication. In comparison to macro-expressions, micro-expressions are more challenging to be analyzed due to the short span of time and the fine-grained changes. In recent years, micro-expression recognition (MER) has drawn much attention because it can benefit a wide range of applications, e.g., police interrogation, clinical diagnosis, depression analysis, and business negotiation. In this survey, we offer a fresh overview to discuss new research directions and challenges these days for MER tasks. For example, we review MER approaches from three novel aspects: macro-to-micro adaptation, recognition based on key apex frames, and recognition based on facial action units. Moreover, to mitigate the problem of limited and biased ME data, synthetic data generation is surveyed for the diversity enrichment of micro-expression data. Since micro-expression spotting can boost micro-expression analysis, the state-of-the-art spotting works are also introduced in this paper. At last, we discuss the challenges in MER research and provide potential solutions as well as possible directions for further investigation. © 2010-2012 IEEE.

关键词： Surveys

来源：评论

学校读者我要写书评

暂无评论

Textual training for the hassle-free removal of unwanted visual data: case studies on OOD and hateful image detection 24

Textual training for the hassle-free removal of unwanted vis...

引用

Proceedings of the 38th International Conference on Neural Information Processing Systems

作者： Saehyung Lee Jisoo Mok Sangha Park Yongho Shin Dahuin Jung Sungroh Yoon Department of Electrical and Computer Engineering Seoul National University Qualcomm Korea YH Seoul South Korea School of Computer Science and Engineering Soongsil University Department of Electrical and Computer Engineering and Interdisciplinary Program in Artificial Intelligence Seoul National University

ISBN: (纸本)9798331314385

In our study, we explore methods for detecting unwanted content lurking in visual datasets. We provide a theoretical analysis demonstrating that a model capable of successfully partitioning visual data can be obtained using only textual data. Based on the analysis, we propose Hassle-Free Textual Training (HFTT), a streamlined method capable of acquiring detectors for unwanted visual content, using only synthetic textual data in conjunction with pre-trained vision-language models. HFTT features an innovative objective function that significantly reduces the necessity for human involvement in data annotation. Furthermore, HFTT employs a clever textual data synthesis method, effectively emulating the integration of unknown visual data distribution into the training process at no extra cost. The unique characteristics of HFTT extend its utility beyond traditional out-of-distribution detection, making it applicable to tasks that address more abstract concepts. We complement our analyses with experiments in out-of-distribution detection and hateful image detection. Our codes are available at https://***/Saehyung-Lee/HFTT

关键词：

来源：评论

学校读者我要写书评

暂无评论

Dynamic Numerical Studies of a Rotorcraft Entering and Exiting Rectangular Tunnel 19

Dynamic Numerical Studies of a Rotorcraft Entering and Exiti...

引用

19th IEEE International Conference on e-Business engineering, ICEBE 2023

作者： Hsu, Uzu-Kuei Chang, Hong-Bin Tsai, Yao-Yu Tai, Chang-Hsien National Pingtung University of Science and Technology Bachelor Program in Artificial Intelligence and Mechatronics Kaohsiung City Taiwan National Pingtung University of Science and Technology Scerdc General Research Service Center Kaohsiung City Taiwan National Pingtung University of Science and Technology Dept. of Vehicle Engineering Kaohsiung City Taiwan

ISBN: (纸本)9798350325553

In recent years, the utilization of multi-rotor drones has seen a steady rise. Unmanned aerial vehicles (UAV) have found diverse applications, including aerial photography, transportation, military operations, and agriculture. The advent of these compact flying machines offers humanity a range of convenient and versatile choices across various sectors. Although unmanned aerial vehicles hold significant practical value, their stable flight is contingent on favorable weather conditions. Consequently, it becomes crucial to investigate the influence of environmental airflow on aircraft stability. This is particularly important for small machines like rotary-wing aircraft operating in confined spaces, where understanding the aerodynamic effects of the flow field is crucial to avert potential crashes. This study delves into the variations in the flow field during the entry and exit of a single rotor into a tunnel. Utilizing dynamic simulations, it examines how tunnels impact the rotor's flow field and analyzes thrust curves to understand dynamic rotor behavior. The study also explores the effect of vortex generation on the rotor and employs a simple square tunnel to assess how tunnel size and flight speed influence the rotor's flow field during flight. The findings hold potential as reference points to enhance flight stability during tunnel flights. © 2023 IEEE.

关键词： Vortex flow

来源：评论

学校读者我要写书评

暂无评论

Comments on a Computation-Transferable Authenticated Key Agreement Protocol for Smart Healthcare

Comments on a Computation-Transferable Authenticated Key Agr...

引用

International Conference on Applied System Innovation (ICASI)

作者： Ya-Fen Chang Chung-Yi Tsai Wei-Liang Tai Department of Computer Science and Information Engineering National Taichung University of Science and Technology Taichung Taiwan Bachelor Degree Program of Artificial Intelligence National Taichung University of Science and Technology Taichung Taiwan

Recently, Wang et al. proposed a computationally transferable authenticated key agreement protocol for smart healthcare by adopting the certificateless public-key cryptography. They claimed that their protocol could ensure privacy, resist various attacks, and possess superior properties. After analyzing their protocol, we find that it suffers from some flaws. Firstly, user privacy is not ensured as claimed. Secondly, some statements are inaccurate or missing. Thirdly, it cannot resist DoS attack. In this paper, the details of how these flaws threaten Wang et al.’s protocol are shown.

关键词：

来源：评论

学校读者我要写书评

暂无评论

DDD: A Perceptually Superior Low-Response-Time DNN-Based Declipper

DDD: A Perceptually Superior Low-Response-Time DNN-Based Dec...

引用

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

作者： Jayeon Yi Junghyun Koo Kyogu Lee Dept. of Electrical Engineering and Computer Science University of Michigan Dept. of Intelligence and Information Seoul National University Interdisciplinary Program in Artificial Intelligence Seoul National University Artificial Intelligence Institute Seoul National University

Clipping is a common nonlinear distortion that occurs whenever the input or output of an audio system exceeds the supported range. This phenomenon undermines not only the perception of speech quality but also downstream processes utilizing the disrupted signal. Therefore, a real-time-capable, robust, and low-response-time method for speech declipping (SD) is desired. In this work, we introduce DDD (Demucs-Discriminator-Declipper), a real-time-capable speech-declipping deep neural network (DNN) that requires less response time by design. We first observe that a previously untested real-time-capable DNN model, Demucs, exhibits a reasonable declipping performance. Then we utilize adversarial learning objectives to increase the perceptual quality of output speech without additional inference overhead. Subjective evaluations on harshly clipped speech shows that DDD outperforms the baselines by a wide margin in terms of speech quality. We perform detailed waveform and spectral analyses to gain an insight into the output behavior of DDD in comparison to the baselines. Finally, our streaming simulations also show that DDD is capable of sub-decisecond mean response times, outperforming the state-of-the-art DNN approach by a factor of six.

关键词：

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：