检索结果-内蒙古大学图书馆

arXiv 2022年

作者： Lu, Haoyu Zhou, Qiongyi Fei, Nanyi Lu, Zhiwu Ding, Mingyu Wen, Jingyuan Du, Changde Zhao, Xin Sun, Hao He, Huiguang Wen, Ji-Rong Gaoling School of Artificial Intelligence Renmin University of China Beijing100872 China Beijing Key Laboratory of Big Data Management and Analysis Methods Beijing100872 China Research Center for Brain-inspired Intelligence National Laboratory of Pattern Recognition Institute of Automation Chinese Academy of Sciences Beijing100190 China School of Artificial Intelligence University of Chinese Academy of Sciences Beijing100049 China School of Information Renmin University of China Beijing100872 China The University of Hong Kong Pokfulam Hong Kong Beijing Academy of Artificial Intelligence Beijing China

Multimodal learning, especially large-scale multimodal pre-training, has developed rapidly over the past few years and led to the greatest advances in artificial intelligence (AI). Despite its effectiveness, understanding the underlying mechanism of multimodal pre-training models still remains a grand challenge. Revealing the explainability of such models is likely to enable breakthroughs of novel learning paradigms in the AI field. To this end, given the multimodal nature of the human brain, we propose to explore the explainability of multimodal learning models with the aid of non-invasive brain imaging technologies such as functional magnetic resonance imaging (fMRI). Concretely, we first present a newly-designed multimodal foundation model pre-trained on 15 million image-text pairs, which has shown strong multimodal understanding and generalization abilities in a variety of cognitive downstream tasks. Further, from the perspective of neural encoding (based on our foundation model), we find that both visual and lingual encoders trained multimodally are more brain-like compared with unimodal ones. Particularly, we identify a number of brain regions where multimodally-trained encoders demonstrate better neural encoding performance. This is consistent with the findings in existing studies on exploring brain multi-sensory integration. Therefore, we believe that multimodal foundation models are more suitable tools for neuroscientists to study the multimodal signal processing mechanisms in the human brain. Our findings also demonstrate the potential of multimodal foundation models as ideal computational simulators to promote both AI-for-brain and brain-for-AI research. Copyright © 2022, The Authors. All rights reserved.

关键词： Brain

来源：评论

学校读者我要写书评

暂无评论

PC-GAIN: Pseudo-label Conditional Generative Adversarial Imputation Networks for Incomplete Data

arXiv

引用

arXiv 2020年

作者： Wang, Yufeng Li, Dan Li, Xiang Yang, Min School of Mathematics and Information Sciences Yantai University Yantai China Research Center for Brain-inspired Intelligence National Laboratory of Pattern Recognition Institute of Automation Chinese Academy of Sciences Beijing China Software Engineering Institute East China Normal University Shanghai China

Datasets with missing values are very common in real world applications. GAIN, a recently proposed deep generative model for missing data imputation, has been proved to outperform many state-of-the-art methods. But GAIN only uses a reconstruction loss in the generator to minimize the imputation error of the non-missing part, ignoring the potential category information which can reflect the relationship between samples. In this paper, we propose a novel unsupervised missing data imputation method named PC-GAIN, which utilizes potential category information to further enhance the imputation power. Specifically, we first propose a pre-training procedure to learn potential category information contained in a subset of low-missing-rate data. Then an auxiliary classifier is determined using the synthetic pseudo-labels. Further, this classifier is incorporated into the generative adversarial framework to help the generator to yield higher quality imputation results. The proposed method can improve the imputation quality of GAIN significantly. Experimental results on various benchmark datasets show that our method is also superior to other baseline approaches. Our code is available at https://***/WYu-Feng/pc-gain. Copyright © 2020, The Authors. 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

CUGE: A Chinese Language Understanding and Generation Evaluation Benchmark

arXiv

引用

arXiv 2021年

作者： Yao, Yuan Dong, Qingxiu Guan, Jian Cao, Boxi Zhang, Zhengyan Xiao, Chaojun Wang, Xiaozhi Qi, Fanchao Bao, Junwei Nie, Jinran Zeng, Zheni Gu, Yuxian Zhou, Kun Huang, Xuancheng Li, Wenhao Ren, Shuhuai Lu, Jinliang Xu, Chengqiang Wang, Huadong Zeng, Guoyang Zhou, Zile Zhang, Jiajun Li, Juanzi Huang, Minlie Yan, Rui He, Xiaodong Wan, Xiaojun Zhao, Xin Sun, Xu Liu, Yang Liu, Zhiyuan Han, Xianpei Yang, Erhong Sui, Zhifang Sun, Maosong Department of Computer Science and Technology Tsinghua University China MOE Key Lab of Computational Linguistics School of EECS Peking University China Institute of Software Chinese Academy of Sciences China JD AI Research Beijing China School of Information Science Beijing Language and Culture University China School of Information Renmin University of China China National Laboratory of Pattern Recognition Institute of Automation CAS China Gaoling School of Artificial Intelligence Renmin University of China China Wangxuan Institute of Computer Technology Peking University Beijing Academy of Artificial Intelligence China

Realizing general-purpose language intelligence has been a longstanding goal for natural language processing, where standard evaluation benchmarks play a fundamental and guiding role. We argue that for general-purpose language intelligence evaluation, the benchmark itself needs to be comprehensive and systematic. To this end, we propose CUGE, a Chinese Language Understanding and Generation Evaluation benchmark with the following features: (1) Hierarchical benchmark framework, where datasets are principally selected and organized with a language capability-task-dataset hierarchy. (2) Multilevel scoring strategy, where different levels of model performance are provided based on the hierarchical framework. To facilitate CUGE, we provide a public leaderboard that can be customized to support flexible model judging criteria. Evaluation results on representative pre-trained language models indicate ample room for improvement towards general-purpose language intelligence. CUGE is publicly available at ***. Copyright © 2021, The Authors. All rights reserved.

关键词： Natural language processing systems

来源：评论

学校读者我要写书评

暂无评论

DAmageNet: A universal adversarial dataset

arXiv

引用

arXiv 2019年

作者： Chen, Sizhe Huang, Xiaolin He, Zhengbao Sun, Chengjin Institute of Image Processing and Pattern Recognition Shanghai Jiao Tong University MOE Key Laboratory of System Control and Information Processing 800 Dongchuan Road Shanghai200240 China

It is now well known that deep neural networks (DNNs) are vulnerable to adversarial attack. Adversarial samples are similar to the clean ones, but are able to cheat the attacked DNN to produce incorrect predictions in high confidence. But most of the existing adversarial attacks have high success rate only when the information of the attacked DNN is well-known or could be estimated by massive queries. A promising way is to generate adversarial samples with high transferability. By this way, we generate 96020 transferable adversarial samples from original ones in ImageNet. The average difference, measured by root means squared deviation, is only around 3.8 on average. However, the adversarial samples are misclassified by various models with an error rate up to 90%. Since the images are generated independently with the attacked DNNs, this is essentially zero-query adversarial attack. We call the dataset DAmageNet, which is the first universal adversarial dataset that beats many models trained in ImageNet. By finding the drawbacks, DAmageNet could serve as a benchmark to study and improve robustness of DNNs. DAmageNet could be downloaded in http://***/Show/56/122 Copyright © 2019, 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

Refining visceral adipose tissue quantification: Influence of sex, age, and BMI on single slice estimation in 3D MRI of the German National Cohort

引用

Zeitschrift fur Medizinische Physik 2025年

作者： Haueise, Tobias Schick, Fritz Stefan, Norbert Grune, Elena von Itter, Marc-Nicolas Kauczor, Hans-Ulrich Nattenmüller, Johanna Norajitra, Tobias Nonnenmacher, Tobias Rospleszcz, Susanne Maier-Hein, Klaus H. Schlett, Christopher L. Weiss, Jakob B. Fischer, Beate Jöckel, Karl-Heinz Krist, Lilian Niendorf, Thoralf Peters, Annette Sedlmeier, Anja M. Willich, Stefan N. Bamberg, Fabian Machann, Jürgen Institute for Diabetes Research and Metabolic Diseases Helmholtz Munich at the University of Tübingen Tübingen Germany Tübingen Germany Section on Experimental Radiology Department of Diagnostic and Interventional Radiology University Hospital Tübingen Tübingen Germany Department of Internal Medicine Division of Diabetology Endocrinology and Nephrology University of Tübingen Tübingen Germany Department of Diagnostic and Interventional Radiology University Hospital Heidelberg Heidelberg Germany Institute of Radiology and Nuclear Medicine Hirslanden Klinik St. Anna Lucerne Switzerland Department of Diagnostic and Interventional Radiology Medical Center Faculty of Medicine University of Freiburg Freiburg Germany Division of Medical Image Computing German Cancer Research Center Heidelberg Germany Pattern Analysis and Learning Group Department of Radiation Oncology University Hospital Heidelberg Heidelberg Germany Department of Epidemiology and Preventive Medicine University of Regensburg Germany Center for Translational Oncology University Hospital Regensburg Germany Regensburg Germany Berlin Germany Berlin Germany University Hospital Essen Essen Germany Department of Epidemiology Institute for Medical Information Processing Biometry and Epidemiology Ludwig-Maximilians-Universität Munich Germany Institute of Epidemiology Helmholtz Munich Environmental Health Center Neuherberg Germany Partner Site Munich Heart Alliance Munich Germany Partner Site Neuherberg Neuherberg Germany Institute of Social Medicine Epidemiology and Health Economics Charité – Universitätsmedizin Berlin Berlin Germany

Objectives: High prevalence of visceral obesity and its associated complications underscore the importance of accurately quantifying visceral adipose tissue (VAT) depots. While whole-body MRI offers comprehensive insights into adipose tissue distribution, it is resource-intensive. Alternatively, evaluation of defined single slices provides an efficient approach for estimation of total VAT volume. This study investigates the influence of sex-, age-, and BMI on VAT distribution along the craniocaudal axis and total VAT volume obtained from single slice versus volumetric assessment in 3D MRI and aims to identify age-independent locations for accurate estimation of VAT volume from single slice assessment. Materials and methods: This secondary analysis of the prospective population-based German National Cohort (NAKO) included 3D VIBE Dixon MRI from 11,191 participants (screened between May 2014 and December 2016). VAT and spine segmentations were automatically generated using fat-selective images. Standardized craniocaudal VAT profiles were generated. Axial percentage of total VAT was used for identification of reference locations for volume estimation of VAT from a single slice. Results: Data from 11,036 participants (mean age, 52 ± 11 years, 5681 men) were analyzed. Craniocaudal VAT distribution differed qualitatively between men/women and with respect to age/BMI. Age-independent single slice VAT estimates demonstrated strong correlations with reference VAT volumes. Anatomical locations for accurate VAT estimation varied with sex/BMI. Conclusions: The selection of reference locations should be different depending on BMI groups, with a preference for caudal shifts in location with increasing BMI. For women with obesity (BMI >30 kg/m2), the L1 level emerges as the optimal reference location. © 2025 The Author(s)

关键词： Magnetic resonance imaging

来源：评论

学校读者我要写书评

暂无评论

Current Progress and Challenges in Large-scale 3D Mitochondria Instance Segmentation

TechRxiv

引用

TechRxiv 2023年

作者： Franco-Barranco, Daniel Lin, Zudi Jang, Won-Dong Wang, Xueying Shen, Qijia Yin, Wenjie Fan, Yutian Li, Mingxing Chen, Chang Xiong, Zhiwei Xin, Rui Liu, Hao Chen, Huai Li, Zhili Zhao, Jie Chen, Xuejin Pape, Constantin Conrad, Ryan De Folter, Jozefus Nightingale, Luke Jones, Martin L. Liu, Yanling Ziaei, Dorsa Huschauer, Stephan Arganda-Carreras, Ignacio Pfister, Hanspeter Wei, Donglai The Department of Computer Science and Artificial Intelligence University of the Basque Country Donostia-San Sebastian Spain San Sebastian Spain Ikerbasque Basque Foundation for Science Bilbao Spain Biofisika Institute CSIC UPV/EHU Bilbao Spain Harvard University All-ston MA United States The Department of Molecular and Cellular Biology Harvard University CambridgeMA United States The Wellcome Centre for Integrative Neuroimaging FMRIB Nuffield Department of Clinical Neurosciences University of Oxford Oxford United Kingdom University of Science and Technology of China Anhui China The Institute of Image Processing and Pattern Recognition Department of Automation Shanghai Jiao Tong University Shanghai China The National Engineering Laboratory for Brain-inspired Intelligence Technology and Application University of Science and Technology of China Anhui China The Georg-August University Goettingen Germany The Center for Molecular Microscopy Center for Cancer Research National Cancer Institute National Institutes of Health Bethesda United States The Cancer Research Technology Program Frederick National Laboratory for Cancer Research Frederick United States The Francis Crick Institute London United Kingdom The Advanced Biomedical Computational Science Group Frederick National Laboratory for Cancer Research FrederickMD United States The Computer Science Department Boston College Chestnut Hill MA United States

In this paper, we present the results of the MitoEM challenge on mitochondria 3D instance segmentation from electron microscopy images, organized in conjunction with the IEEE-ISBI 2021 conference. Our benchmark dataset consists of two large-scale 3D volumes, one from human and one from rat cortex tissue, which are 3,600 times larger than previously used datasets. At the time of paper submission, 257 participants had registered for the challenge, 14 teams had submitted their results, and six teams participated in the challenge workshop. Here, we present eight top-performing approaches from the challenge participants, along with our own baseline strategies. Posterior to the challenge, annotation errors in the ground truth were corrected without altering the final ranking. Additionally, we present a retrospective evaluation of the scoring system which revealed that (1) the challenge metric was permissive with the false positive predictions and (2) the size-based grouping of instances did not correctly categorize mitochondria of interest. Thus, we propose a new scoring system that better reflects the correctness of the segmentation results. Although several of the top methods are compared favorably to our own baselines, substantial errors remain unsolved for mitochondria with challenging morphologies. Thus, the challenge remains open for submission and automatic evaluation, with all volumes available for download. © 2023, CC BY.

关键词： Electron microscopy

来源：评论

学校读者我要写书评

暂无评论

Mem Brain: An Easy-to-Use Online Webserver for Transmembrane Protein Structure Prediction

引用

Nano-Micro Letters 2018年第1期10卷 12-19页

作者： Xi Yin Jing Yang Feng Xiao Yang Yang Hong-Bin Shen Institute of Image Processing and Pattern Recognition Shanghai Jiao Tong University Key Laboratory of System Control and Information Processing Ministry of Education of China Department of Computer Science Shanghai Jiao Tong University Key Laboratory of Shanghai Education Commission for Intelligent Interaction and Cognitive Engineering

Membrane proteins are an important kind of proteins embedded in the membranes of cells and play crucial roles in living organisms, such as ion channels,transporters, receptors. Because it is difficult to determinate the membrane protein's structure by wet-lab experiments,accurate and fast amino acid sequence-based computational methods are highly desired. In this paper, we report an online prediction tool called Mem Brain, whose input is the amino acid sequence. Mem Brain consists of specialized modules for predicting transmembrane helices, residue–residue contacts and relative accessible surface area of a-helical membrane proteins. Mem Brain achieves aprediction accuracy of 97.9% of ATMH, 87.1% of AP,3.2 ± 3.0 of N-score, 3.1 ± 2.8 of C-score. Mem BrainContact obtains 62%/64.1% prediction accuracy on training and independent dataset on top L/5 contact prediction,respectively. And Mem Brain-Rasa achieves Pearson correlation coefficient of 0.733 and its mean absolute error of13.593. These prediction results provide valuable hints for revealing the structure and function of membrane *** Brain web server is free for academic use and available at ***/bioinf/Mem Brain/.

关键词： Transmembrane a-helices Structure prediction Machine learning Contact map prediction Relative accessible surface area

来源：评论

学校读者我要写书评

暂无评论

Web Page Classification Algorithm Based on Semi-Supervised Support Vector Machine 2

Web Page Classification Algorithm Based on Semi-Supervised S...

引用

2nd IEEE Advanced information Management, Communicates, Electronic and Automation Control Conference, IMCEC 2018

作者： Huang, Wenqing You, Hui Zhejiang Sci-Tech University Institute of Computer Vision Image Processing and Pattern Recognition Acceptable School of Information Hangzhou China

ISBN: (纸本)9781538618035

Most web page classification algorithms are learning algorithms under the single-instance single-label framework. Multi-Instance Multi-Label learning is a new machine learning framework. MIMLSVM+ algorithm, using degenerate strategy to transform multiple instances into single instances, and then decomposing multiple labels into a series of two types of classification problems, that is, building an SVM for each label. Because the MIMLSVM+ algorithm degrades the multi-label problem into a series of two types of classification problems, the processing of each label will lose the contact information between the labels independently. Therefore, multi-tasking technology is introduced to make use of the multi-tasking learning framework based on nuclear to validate the MIMLSVM+ expand, get E-MIMLSVM+ algorithm. The paper improves E-MIMLSVM+ algorithm by using the semi-supervised learning method. Experimental results show that the proposed method can achieve higher classification accuracy. © 2018 IEEE.

关键词： Learning algorithms

来源：评论

学校读者我要写书评

暂无评论

Moving objects elimination towards enhanced dynamic SLAM fusing LiDAR and mmW-radar

Moving objects elimination towards enhanced dynamic SLAM fus...

引用

IEEE MTT-S International Conference on Microwaves for Intelligent Mobility (ICMIM)

作者： Xiangwei Dang Xingdong Liang Yanlei Li Zheng Rong National Key Laboratory of Microwave Imaging Technology Aerospace Information Research Institute Chinese Academy of Sciences School of Electronic Electrical and Communication Engineering University of Chinese Academy of Sciences Beijing China National Laboratory of Pattern Recognition Institute of Automation Chinese Academy of Sciences Beijing China

ISBN: (数字)9781728167558

ISBN: (纸本)9781728167565

Robust and accurate localization and mapping are essential for autonomous driving. The traditional SLAM methods generally work under the assumption that the environment is static, while in dynamic environment the performance will be degenerate. In this paper, we propose an efficient and effective method to eliminate the influence of dynamic environment on SLAM by fusing LiDAR and mmW-radar, which significantly improves the robustness and accuracy of localization and mapping. The method fully utilizes the advantages of different measurement characteristics of two sensors, efficient moving object detection based on Doppler effect by radar and accurate object segmentation and localization by LiDAR, to remove the moving objects and uses the resulting filtered point cloud as the input of SLAM towards enhanced performance. The proposed approach is evaluated through experiments in various real world scenarios, and the results demonstrate the effectiveness of the method to improve the robustness and accuracy of SLAM in dynamic environments.

关键词： Simultaneous localization and mapping Laser radar Three-dimensional displays Radar measurements Radar detection Sensor phenomena and characterization Robustness

来源：评论

学校读者我要写书评

暂无评论

MoEfication: Transformer Feed-forward Layers are Mixtures of Experts

arXiv

引用

arXiv 2021年

作者： Zhang, Zhengyan Lin, Yankai Liu, Zhiyuan Li, Peng Sun, Maosong Zhou, Jie Dept. of Comp. Sci. & Tech. Institute for AI Tsinghua University Beijing China Beijing National Research Center for Information Science and Technology China Pattern Recognition Center WeChat AI Tencent Inc China International Innovation Center Tsinghua University Shanghai China Beijing Academy of Artificial Intelligence China Tsinghua University China Jiangsu Collaborative Innovation Center for Language Ability Xuzhou China

Recent work has shown that feed-forward networks (FFNs) in pre-trained Transformers are a key component, storing various linguistic and factual knowledge. However, the computational patterns of FFNs are still unclear. In this work, we study the computational patterns of FFNs and observe that most inputs only activate a tiny ratio of neurons of FFNs. This phenomenon is similar to the sparsity of the human brain, which drives research on functional partitions of the human brain. To verify whether functional partitions also emerge in FFNs, we propose to convert a model into its MoE version with the same parameters, namely MoEfication. Specifically, MoEfication consists of two phases: (1) splitting the parameters of FFNs into multiple functional partitions as experts, and (2) building expert routers to decide which experts will be used for each input. Experimental results show that MoEfication can conditionally use 10% to 30% of FFN parameters while maintaining over 95% original performance for different models on various downstream tasks. Besides, MoEfication brings two advantages: (1) it significantly reduces the FLOPS of inference, i.e., 2x speedup with 25% of FFN parameters, and (2) it provides a fine-grained perspective to study the inner mechanism of FFNs. The source code of this paper can be obtained from https://***/thunlp/MoEfication. Copyright © 2021, The Authors. All rights reserved.

关键词： Brain

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：