检索结果-内蒙古大学图书馆

arXiv 2022年

作者： Li, Jun Tan, Zichang Wan, Jun Lei, Zhen Guo, Guodong CBSR&NLPR Institute of Automation Chinese Academy of Sciences Beijing China School of Artificial Intelligence University of Chinese Academy of Sciences Beijing China Institute of Deep Learning Baidu Research Beijing China National Engineering Laboratory for Deep Learning Technology and Application Beijing China Centre for Artificial Intelligence and Robotics Hong Kong Institute of Science&Innovation Chinese Academy of Sciences Hong Kong

The networks trained on the long-tailed dataset vary remarkably, despite the same training settings, which shows the great uncertainty in long-tailed learning. To alleviate the uncertainty, we propose a Nested Collaborative learning (NCL), which tackles the problem by collaboratively learning multiple experts together. NCL consists of two core components, namely Nested Individual learning (NIL) and Nested Balanced Online Distillation (NBOD), which focus on the individual supervised learning for each single expert and the knowledge transferring among multiple experts, respectively. To learn representations more thoroughly, both NIL and NBOD are formulated in a nested way, in which the learning is conducted on not just all categories from a full perspective but some hard categories from a partial perspective. Regarding the learning in the partial perspective, we specifically select the negative categories with high predicted scores as the hard categories by using a proposed Hard Category Mining (HCM). In the NCL, the learning from two perspectives is nested, highly related and complementary, and helps the network to capture not only global and robust features but also meticulous distinguishing ability. Moreover, self-supervision is further utilized for feature enhancement. Extensive experiments manifest the superiority of our method with outperforming the state-of-the-art whether by using a single model or an ensemble. Code is available at https://***/Bazinga699/NCL Copyright © 2022, The Authors. All rights reserved.

关键词： Distillation

来源：评论

学校读者我要写书评

暂无评论

Cross-ethnicity face anti-spoofing recognition challenge: A review

arXiv

引用

arXiv 2020年

作者： Liu, Ajian Li, Xuan Wan, Jun Liang, Yanyan Escalera, Sergio Escalante, Hugo Jair Madadi, Meysam Jin, Yi Wu, Zhuoyuan Yu, Xiaogang Tan, Zichang Yuan, Qi Yang, Ruikun Zhou, Benjia Guo, Guodong Li, Stan Z. Faculty of Information Technology Avenida WaiLong Taipa Macau China School of Computer and Information Technology Beijing Jiaotong University Beijing China National Laboratory of Pattern Recognition Institute of Automation Chinese Academy of Science Beijing China Universitat de Barcelona and Computer Vision Center Barcelona Instituto Nacional de Astrofísica Óptica y Electrónica Puebla Mexico School of Software Beihang University Beijing China Institute of Deep Learning Baidu Research and National Engineering Laboratory for Deep Learning Technology and Application Beijing Westlake University Hangzhou China

Face anti-spoofing is critical to prevent face recognition systems from a security breach. The biometrics community has achieved impressive progress recently due the excellent performance of deep neural networks and the availability of large datasets. Although ethnic bias has been verified to severely affect the performance of face recognition systems, it still remains an open research problem in face anti-spoofing. Recently, a multi-ethnic face anti-spoofing dataset, CASIA-SURF CeFA, has been released with the goal of measuring the ethnic bias. It is the largest up to date cross-ethnicity face anti-spoofing dataset covering 3 ethnicities, 3 modalities, 1;607 subjects, 2D plus 3D attack types, and the first dataset including explicit ethnic labels among the recently released datasets for face *** organized the Chalearn Face Anti-spoofing Attack Detection Challenge which consists of single-modal (e.g., RGB) and multi-modal (e.g., RGB, Depth, Infrared (IR)) tracks around this novel resource to boost research aiming to alleviate the ethnic bias. Both tracks have attracted 340 teams in the development stage, and finally 11 and 8 teams have submitted their codes in the single-modal and multi-modal face anti-spoofing recognition challenges, respectively. All the results were verified and re-ran by the organizing team, and the results were used for the final ranking. This paper presents an overview of the challenge, including its design, evaluation protocol and a summary of results. We analyze the top ranked solutions and draw conclusions derived from the competition. In addition we outline future work directions. Copyright © 2020, The Authors. All rights reserved.

关键词： Large dataset

来源：评论

学校读者我要写书评

暂无评论

Domain-Aware SE network for Sketch-Based Image Retrieval with Multiplicative Euclidean Margin Softmax

arXiv

引用

arXiv 2018年

作者： Lu, Peng Yang, Wenming Huang, Gao Guo, Guodong Lin, Hangyu Fu, Yanwei Shenzhen International Graduate School Tsinghua University Shenzhen China Shenzhen International Graduate School Department of Electronic Engineering Tsinghua University Shenzhen China Department of Automation Tsinghua University Beijing China IDL Baidu Research National Engineering Lab for Deep Learning Technology and Application Beijing China School of Data Science Fudan University Shanghai China

This paper proposes a novel approach for Sketch-Based Image Retrieval (SBIR), for which the key is to bridge the gap between sketches and photos in terms of the data representation. Inspired by channel-wise attention explored in recent years, we present a Domain-Aware Squeeze-and-Excitation (DASE) network, which seamlessly incorporates the prior knowledge of sample sketch or photo into SE module and make the SE module capable of emphasizing appropriate channels according to domain signal. Accordingly, the proposed network can switch its mode to achieve a better domain feature with lower intra-class discrepancy. Moreover, while previous works simply focus on minimizing intra-class distance and maximizing inter-class distance, we introduce a loss function, named Multiplicative Euclidean Margin Softmax (MEMS), which introduce multiplicative Euclidean margin into feature space and ensure that the maximum intra-class distance is smaller than the minimum inter-class distance. This facilitates learning a highly discriminative feature space and ensures a more accurate image retrieval result. Extensive experiments are conducted on two widely used SBIR benchmark datasets. Our approach achieves better results on both datasets, surpassing the state-of-the-art methods by a large margin. Copyright © 2018, The Authors. All rights reserved.

关键词： Large dataset

来源：评论

学校读者我要写书评

暂无评论

Aggregation Signature for Small Object Tracking

arXiv

引用

arXiv 2019年

作者： Liu, Chunlei Ding, Wenrui Yang, Jinyu Murino, Vittorio Zhang, Baochang Han, Jungong Guo, Guodong School of Electrical and Information Engineering Beihang University Beijing China Unmanned System Research Institute Beihang University Beijing China School of Computer Science University of Birmingham British United Kingdom University of Verona Verona Italy Pattern Analysis and Computer Vision department Istituto Italiano di Tecnologia Genoa Italy School of Automation Science and Electrical Engineering Beihang University Beijing China Shenzhen Academy of Aerospace Technology Shenzhen China WMG Data Science Group University of Warwick CoventryCV4 7AL United Kingdom Institute of Deep Learning Baidu Research and National Engineering Laboratory for Deep Learning Technology and Application

—Small object tracking becomes an increasingly important task, which however has been largely unexplored in computer vision. The great challenges stem from the facts that: 1) small objects show extreme vague and variable appearances, and 2) they tend to be lost easier as compared to normal-sized ones due to the shaking of lens. In this paper, we propose a novel aggregation signature suitable for small object tracking, especially aiming for the challenge of sudden and large drift. We make three-fold contributions in this work. First, technically, we propose a new descriptor, named aggregation signature, based on saliency, able to represent highly distinctive features for small objects. Second, theoretically, we prove that the proposed signature matches the foreground object more accurately with a high probability. Third, experimentally, the aggregation signature achieves a high performance on multiple datasets, outperforming the state-of-the-art methods by large margins. Moreover, we contribute with two newly collected benchmark datasets, i.e., small90 and small112, for visually small object tracking. The datasets will be available in https://***/bczhangbczhang/. Copyright © 2019, The Authors. All rights reserved.

关键词： Large dataset

来源：评论

学校读者我要写书评

暂无评论

ChaLearn looking at people: IsoGD and ConGD large-scale RGB-D gesture recognition

arXiv

引用

arXiv 2019年

作者： Wan, Jun Lin, Chi Wen, Longyin Li, Yunan Miao, Qiguang Escalera, Sergio Anbarjafari, Gholamreza Guyon, Isabelle Guo, Guodong Li, Stan Z. National Laboratory of Pattern Recognition Institute of Automation Chinese Academy of Sciences Beijing100190 China JD Finance Mountain ViewCA United States University of Southern California Los AngelesCA90089-0911 United States School of Computer Science and Technology Xidian University & Xi'an Key Laboratory of Big Data and Intelligent Vision 2nd South Taibai Road Xi'an710071 China Universitat de Barcelona Computer Vision Center Spain iCV Lab Institute of Technology University of Tartu Estonia Faculty of Engineering Hasan Kalyoncu University Gaziantep Turkey Institute of Digital Technologies Loughborough University London United Kingdom ChaLearn United States University Paris-Saclay France institute of Deep Learning Baidu Research National Engineering Laboratory for Deep Learning Technology and Application China

The ChaLearn large-scale gesture recognition challenge has been run twice in two workshops in conjunction with the International Conference on Pattern Recognition (ICPR) 2016 and International Conference on Computer Vision (ICCV) 2017, attracting more than 200 teams around the world. This challenge has two tracks, focusing on isolated and continuous gesture recognition, respectively. This paper describes the creation of both benchmark datasets and analyzes the advances in large-scale gesture recognition based on these two datasets. We discuss the challenges of collecting large-scale ground-truth annotations of gesture recognition, and provide a detailed analysis of the current state-of-the-art methods for large-scale isolated and continuous gesture recognition based on RGB-D video sequences. In addition to recognition rate and mean jaccard index (MJI) as evaluation metrics used in our previous challenges, we also introduce the corrected segmentation rate (CSR) metric to evaluate the performance of temporal segmentation for continuous gesture recognition. Furthermore, we propose a bidirectional long short-term memory (Bi-LSTM) baseline method, determining the video division points based on the skeleton points extracted by convolutional pose machine (CPM). Experiments demonstrate that the proposed Bi-LSTM outperforms the state-of-the-art methods with an absolute improvement of 8.1% (from 0.8917 to 0.9639) of CSR. Copyright © 2019, The Authors. All rights reserved.

关键词： Long short-term memory

来源：评论

学校读者我要写书评

暂无评论

The Speech Synthesis of Yi Language Based on DNN

The Speech Synthesis of Yi Language Based on DNN

引用

Information, Media and engineering (IJCIM), International Joint Conference on

作者： Xiaolong Bu Hongwu Yang Weizhao Zhang College of Physics and Electronic Engineering Northwest Normal University Lanzhou China School of Educational Technology National and provincial Joint Engineering Laboratory of Learning Analysis Technology in Online Education Northwest Normal University Lanzhou China College of Physics and Electronic Engineering Engineering Research Center of Gansu Province for Intelligent Information Technology and Application Northwest Normal University Lanzhou China

ISBN: (数字)9781728155869

ISBN: (纸本)9781728155876

This paper is mainly about a speech synthesis system based on deep Neural Network (DNN) model of Yi languages, a kind of minority language in China. The system is composed of relatively complete text analysis of Yi, model training and speech synthesis module. Especially in front-end, the word segmentation, pause handling, word-to-phoneme conversion and label processing are used to analysis text of Yi language. We designed the question set for decision tree of DNN model training and used vocoder: WORLD for synthesis. The system achieves a relatively good Mean Opinion Score (MOS) of 3.93 by Yi undergraduates as evaluators compared with a MOS of 4.58 of original speech. To investigate the factors affecting the quality of synthesized Yi speech, this paper also objectively evaluates the performance of different training set and DNN model. The system successfully synthesized Yi speech for the first time and synthesized speech is relatively good as the result of an only complete minority language speech synthesis system.

关键词： Speech synthesis Text analysis Training Analytical models Hidden Markov models Dictionaries

来源：评论

学校读者我要写书评

暂无评论

Kham Dialect Speech Synthesis Based on deep learning

Kham Dialect Speech Synthesis Based on Deep Learning

引用

Information, Media and engineering (IJCIM), International Joint Conference on

作者： Weizhao Zhang Hongwu Yang Xiaolong Bu College of Physics and Electronic Engineering Engineering Research Center of Gansu Province for Intelligent Information Technology and Application Northwest Normal University Lanzhou China School of Educational Technology National and Provincial Joint Engineering Laboratory of Learning Analysis Technology in Online Education College of Physics and Electronic Engineering Northwest Normal University Lanzhou China College of Physics and Electronic Engineering Northwest Normal University Lanzhou China

ISBN: (数字)9781728155869

ISBN: (纸本)9781728155876

In this paper, we constructed speech synthesis corpus of Kham dialect. At the same time, we designed SAMP-Kham machine-readable phonetic label of Kham dialect, and proposed a framework of Kham dialect speech synthesis based on deep learning. The deep learning architecture includes deep neural network (DNN), hybrid long short-term memory (LSTM) and hybrid Bidirectional long short-term memory (BLSTM). The objective and subjective evaluations test showed that quality of synthesized speech of Kham dialect was satisfied.

关键词： Speech synthesis Machine learning Hidden Markov models Acoustics Adaptation models Training Neural networks

来源：评论

学校读者我要写书评

暂无评论

Transformer-based Annotation Bias-aware Medical Image Segmentation

arXiv

引用

arXiv 2023年

作者： Liao, Zehui Xie, Yutong Hu, Shishuai Xia, Yong National Engineering Laboratory for Integrated Aero-Space-Ground-Ocean Big Data Application Technology School of Computer Science and Engineering Northwestern Polytechnical University Xi’an710072 China Australian Institute for Machine Learning The University of Adelaide AdelaideSA Australia Ningbo Institute of Northwestern Polytechnical University Ningbo315048 China Research and Development Institute Northwestern Polytechnical University in Shenzhen Shenzhen518057 China

Manual medical image segmentation is subjective and suffers from annotator-related bias, which can be mimicked or amplified by deep learning methods. Recently, researchers have suggested that such bias is the combination of the annotator preference and stochastic error, which are modeled by convolution blocks located after decoder and pixel-wise independent Gaussian distribution, respectively. It is unlikely that convolution blocks can effectively model the varying degrees of preference at the full resolution level. Additionally, the independent pixel-wise Gaussian distribution disregards pixel correlations, leading to a discontinuous boundary. This paper proposes a Transformer-based Annotation Bias-aware (TAB) medical image segmentation model, which tackles the annotator-related bias via modeling annotator preference and stochastic errors. TAB employs the Transformer with learnable queries to extract the different preference-focused features. This enables TAB to produce segmentation with various preferences simultaneously using a single segmentation head. Moreover, TAB takes the multivariant normal distribution assumption that models pixel correlations, and learns the annotation distribution to disentangle the stochastic error. We evaluated our TAB on an OD/OC segmentation benchmark annotated by six annotators. Our results suggest that TAB outperforms existing medical image segmentation models which take into account the annotator-related bias. © 2023, CC BY-NC-ND.

关键词： Gaussian distribution

来源：评论

学校读者我要写书评

暂无评论

deepMD-kit v2: A software package for deep Potential models

arXiv

引用

arXiv 2023年

作者： Zeng, Jinzhe Zhang, Duo Lu, Denghui Mo, Pinghui Li, Zeyu Chen, Yixiao Rynik, Marián Huang, Li'ang Li, Ziyao Shi, Shaochen Wang, Yingze Ye, Haotian Tuo, Ping Yang, Jiabin Ding, Ye Li, Yifan Tisi, Davide Zeng, Qiyu Bao, Han Xia, Yu Huang, Jiameng Muraoka, Koki Wang, Yibo Chang, Junhan Yuan, Fengbo Bore, Sigbjørn Løland Cai, Chun Lin, Yinnian Wang, Bo Xu, Jiayan Zhu, Jia-Xin Luo, Chenxing Zhang, Yuzhi Goodall, Rhys E.A. Liang, Wenshuo Singh, Anurag Kumar Yao, Sikai Zhang, Jingchao Wentzcovitch, Renata Han, Jiequn Liu, Jie Jia, Weile York, Darrin M. Weinan, E. Car, Roberto Zhang, Linfeng Wang, Han Laboratory for Biomolecular Simulation Research Institute for Quantitative Biomedicine Department of Chemistry and Chemical Biology Rutgers University PiscatawayNJ08854 United States AI for Science Institute Beijing100080 China DP Technology Beijing100080 China Academy for Advanced Interdisciplinary Studies Peking University Beijing100871 China HEDPS CAPT College of Engineering Peking University Beijing100871 China College of Electrical and Information Engineering Hunan University Changsha China Yuanpei College Peking University Beijing100871 China Program in Applied and Computational Mathematics Princeton University PrincetonNJ08540 United States Department of Experimental Physics Comenius University Mlynská Dolina F2 Bratislava842 48 Slovakia Center for Quantum Information Institute for Interdisciplinary Information Sciences Tsinghua University Beijing100084 China Center for Data Science Peking University Beijing100871 China ByteDance Research Zhonghang Plaza No. 43 North 3rd Ring West Road Haidian District Beijing China College of Chemistry and Molecular Engineering Peking University Beijing100871 China Baidu Inc. Beijing China Key Laboratory of Structural Biology of Zhejiang Province School of Life Sciences Westlake University Zhejiang Hangzhou China Westlake AI Therapeutics Lab Westlake Laboratory of Life Sciences and Biomedicine Zhejiang Hangzhou China Department of Chemistry Princeton University PrincetonNJ08544 United States SISSA Scuola Internazionale Superiore di Studi Avanzati Trieste34136 Italy Laboratory of Computational Science and Modeling Institute of Materials École Polytechnique Fédérale de Lausanne Lausanne1015 Switzerland Department of Physics National University of Defense Technology Hunan Changsha410073 China State Key Lab of Processors Institute of Computing Technology Chinese Academy of Sciences Beijing China University of Chinese Academy of Sciences Beijing China School of Electronics Engineerin

deepMD-kit is a powerful open-source software package that facilitates molecular dynamics simulations using machine learning potentials (MLP) known as deep Potential (DP) models. This package, which was released in 2017, has been widely used in the fields of physics, chemistry, biology, and material science for studying atomistic systems. The current version of deepMD-kit offers numerous advanced features such as deepPot-SE, attention-based and hybrid descriptors, the ability to fit tensile properties, type embedding, model deviation, deep Potential - Range Correction (DPRc), deep Potential Long Range (DPLR), GPU support for customized operators, model compression, non-von Neumann molecular dynamics (NVNMD), and improved usability, including documentation, compiled binary packages, graphical user interfaces (GUI), and application programming interfaces (API). This article presents an overview of the current major version of the deepMD-kit package, highlighting its features and technical details. Additionally, the article benchmarks the accuracy and efficiency of different models and discusses ongoing developments. © 2023, CC BY-NC-ND.

关键词： Molecular dynamics

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：