检索结果-内蒙古大学图书馆

R2-Net: Relation of relation learning network for sentence semantic matching

学校读者我要写书评

暂无评论

arXiv 2020年

作者： Zhang, Kun Wu, Le Lv, Guangyi Wang, Meng Chen, Enhong Ruan, Shulan School of Computer Science and Information Engineering Hefei University of Technology China Institute of Artificial Intelligence Hefei Comprehensive National Science Center China Anhui Province Key Laboratory of Big Data Analysis and Application University of Science and Technology of China China

Sentence semantic matching is one of the fundamental tasks in natural language processing, which requires an agent to determine the semantic relation among input sentences. Recently, deep neural networks have achieved impressive performance in this area, especially BERT. Despite their effectiveness, most of these models treat output labels as meaningless one-hot vectors, underestimating the semantic information and guidance of relations that these labels reveal, especially for tasks with a small number of labels. To address this problem, we propose a Relation of Relation Learning Network (R2-Net) for sentence semantic matching. Specifically, we first employ BERT to encode the input sentences from a global perspective. Then a CNN-based encoder is designed to capture keywords and phrase information from a local perspective. To fully leverage labels for better relation information extraction, we introduce a self-supervised relation of relation classification task for guiding R2-Net to consider more about relations. Meanwhile, a triplet loss is employed to distinguish the intra-class and inter-class relations in a finer granularity. Empirical experiments on two sentence semantic matching tasks demonstrate the superiority of our proposed model. As a byproduct, we have released the codes to facilitate other researches. © 2020, CC BY.

关键词： Natural language processing systems

VisEvent: Reliable Object Tracking via Collaboration of Frame and Event Flows

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Wang, Xiao Li, Jianing Zhu, Lin Zhang, Zhipeng Chen, Zhe Li, Xin Wang, Yaowei Tian, Yonghong Wu, Feng School of Computer Science and Technology Anhui University Hefei230601 China Peng Cheng Laboratory Shenzhen China National Engineering Laboratory for Video Technology School of Electronics Engineering and Computer Science Peking University Beijing China National Laboratory of Pattern Recognition Institute of Automation Chinese Academy of Sciences School of AI University of Chinese Academy of Sciences China The University of Sydney Australia The Cisco-La Trobe Centre for Artificial Intelligence and Internet of Things La Trobe University Australia Edwards Rd Flora Hill3552 Australia The University of Science and Technology of China Hefei China

Different from visible cameras which record intensity images frame by frame, the biologically inspired event camera produces a stream of asynchronous and sparse events with much lower latency. In practice, visible cameras can better perceive texture details and slow motion, while event cameras can be free from motion blurs and have a larger dynamic range which enables them to work well under fast motion and low illumination. Therefore, the two sensors can cooperate with each other to achieve more reliable object tracking. In this work, we propose a large-scale Visible-Event benchmark (termed VisEvent) due to the lack of a realistic and scaled dataset for this task. Our dataset consists of 820 video pairs captured under low illumination, high speed, and background clutter scenarios, and it is divided into a training and a testing subset, each of which contains 500 and 320 videos, respectively. Based on VisEvent, we transform the event flows into event images and construct more than 30 baseline methods by extending current single-modality trackers into dual-modality versions. More importantly, we further build a simple but effective tracking algorithm by proposing a cross-modality transformer, to achieve more effective feature fusion between visible and event data. Extensive experiments on the proposed VisEvent dataset, FE108, COESOT, and two simulated datasets (i.e., OTB-DVS and VOT-DVS), validated the effectiveness of our model. The dataset and source code have been released on: https://***/wangxiao5791509/VisEvent_SOT_Benchmark. Copyright © 2021, The Authors. All rights reserved.

关键词： Cameras

A multi-branch hybrid transformer network for corneal endothelial cell segmentation

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Zhang, Yinglin Higashita, Risa Fu, Huazhu Xu, Yanwu Zhang, Yang Liu, Haofeng Zhang, Jian Liu, Jiang Department of Computer Science and Engineering Southern University of Science and Technology Shenzhen518055 China Cixi Institute of Biomedical Engineering Chinese Academy of Sciences China Guangdong Provincial Key Laboratory of Brain-inspired Intelligent Computation Department of Computer Science and Engineering Southern University of Science and Technology Shenzhen518055 China Research Institute of Trustworthy Autonomous Systems Southern University of Science and Technology Shenzhen518055 China Tomey Corporation Nagoya451-0051 Japan Global Big Data Technologies Centre University of Technology SydneyNSW Australia Inception Institute of Artificial Intelligence United Arab Emirates Intelligent Healthcare Unit Baidu Beijing100085 China

Corneal endothelial cell segmentation plays a vital role in quantifying clinical indicators such as cell density, coefficient of variation, and hexagonality. However, the corneal endothelium’s uneven reflection and the subject’s tremor and movement cause blurred cell edges in the image, which is difficult to segment, and need more details and context information to release this problem. Due to the limited receptive field of local convolution and continuous downsampling, the existing deep learning segmentation methods cannot make full use of global context and miss many details. This paper proposes a Multi-Branch hybrid Transformer Network (MBT-Net) based on the transformer and body-edge branch. Firstly, We use the convolutional block to focus on local texture feature extraction and establish long-range dependencies over space, channel, and layer by the transformer and residual connection. Besides, We use the body-edge branch to promote local consistency and to provide edge position information. On the self-collected dataset TM-EM3000 and public Alisarine dataset, compared with other State-Of-The-Art (SOTA) methods, the proposed method achieves an improvement. Copyright © 2021, The Authors. All rights reserved.

关键词： Endothelial cells

Many-class few-shot learning on multi-granularity class hierarchy

学校读者我要写书评

暂无评论

arXiv 2020年

作者： Liu, Lu Zhou, Tianyi Long, Guodong Jiang, Jing Zhang, Chengqi Centre for Artificial Intelligence FEIT University of Technology Sydney UltimoNSW2007 Australia School of Computer Science & Engineering University of Washington SeattleWA98195 United States

—We study many-class few-shot (MCFS) problem in both supervised learning and meta-learning settings. Compared to the well-studied many-class many-shot and few-class few-shot problems, the MCFS problem commonly occurs in practical applications but has been rarely studied in previous literature. It brings new challenges of distinguishing between many classes given only a few training samples per class. In this paper, we leverage the class hierarchy as a prior knowledge to train a coarse-to-fine classifier that can produce accurate predictions for MCFS problem in both settings. The propose model, "memory-augmented hierarchical-classification network (MahiNet)", performs coarse-to-fine classification where each coarse class can cover multiple fine classes. Since it is challenging to directly distinguish a variety of fine classes given few-shot data per class, MahiNet starts from learning a classifier over coarse-classes with more training data whose labels are much cheaper to obtain. The coarse classifier reduces the searching range over the fine classes and thus alleviates the challenges from "many classes". On architecture, MahiNet firstly deploys a convolutional neural network (CNN) to extract features. It then integrates a memory-augmented attention module and a multi-layer perceptron (MLP) together to produce the probabilities over coarse and fine classes. While the MLP extends the linear classifier, the attention module extends the KNN classifier, both together targeting the "few-shot" problem. We design several training strategies of MahiNet for supervised learning and meta-learning. In addition, we propose two novel benchmark datasets "mcfsImageNet" (as a subset of ImageNet) and "mcfsOmniglot" (re-splitted Omniglot) specially designed for MCFS problem. In experiments, we show that MahiNet outperforms several state-of-the-art models (e.g., prototypical networks and relation networks) on MCFS problems in both supervised learning and meta-learning. Copyright © 2020

关键词： Classification (of information)

Web intelligence (WI) 3.0: in search of a better-connected world to create a future intelligent society

学校读者我要写书评

暂无评论

artificial intelligence Review 2025年第9期58卷

作者： Kuai, Hongzhi Huang, Jimmy X. Tao, Xiaohui Pasi, Gabriella Yao, Yiyu Liu, Jiming Zhong, Ning School of Computer Science and Technology/School of Artificial Intelligence Chongqing University of Posts and Telecommunications Chongqing China Key Laboratory of Big Data Intelligent Computing Chongqing University of Posts and Telecommunications Chongqing China School of Information Technology York University North YorkON Canada School of Mathematics Physics and Computing University of Southern Queensland ToowoombaQLD Australia Department of Informatics Systems and Communication University of Milano-Bicocca Milano Italy Department of Computer Science University of Regina Regina Canada Department of Computer Science Hong Kong Baptist University Kowloon Tong Hong Kong Faculty of Engineering Maebashi Institute of Technology Gunma Maebashi Japan

Over the past two decades, Web intelligence (WI) has emerged as a key field driving the evolution of AI in the connected world, addressing the demands of a future intelligent society. This paper provides a comprehensive review of WI’s contributions since its inception in 2000, spanning three distinct phases: Wisdom World Wide Web (WI 1.0, 2000–2009), Wisdom Web of Things (WI 2.0, 2010–2017), and Wisdom Web of Everything (WI 3.0, since 2018). For each phase, we examine key advancements, challenges, and future directions from the perspectives of both intelligent machines and human experts, highlighting significant societal impacts. To advance WI research, we propose a large language model-based learning framework for topic analysis and trend prediction. Moving beyond single-perspective approaches, we emphasize the Connected intelligence Ecosystem defined by the HIGH5 scheme comprising one goal, two twins, three fundamentals, four functions, and five services that are realized through WI 3.0. This vision serves as a bridge from localized models to a global reference framework for addressing sustainability challenges in future societies. To illustrate the real-world implications of WI 3.0, we present case studies focusing on brain-inspired research, particularly in the intersection of brain intelligence, brain health, and brainternet-fostering interdisciplinary collaboration across diverse research communities. © The Author(s) 2025.

关键词： Intelligent computing

Cross-modality brain tumor segmentation via bidirectional global-to-local unsupervised domain adaptation

学校读者我要写书评

暂无评论

arXiv 2021年

作者： He, Kelei Ji, Wen Zhou, Tao Li, Zhuoyuan Huo, Jing Zhang, Xin Gao, Yang Shen, Dinggang Zhang, Bing Zhang, Junfeng Medical School of Nanjing University Nanjing China The National Institute of Healthcare Data Science Nanjing University Nanjing China The State Key Laboratory for Novel Software Technology Nanjing University Nanjing China School of Computer Science and Technology Nanjing University of Science and Technology Nanjing China Department of Radiology Nanjing Drum Tower Hospital Nanjing University Medical School China School of Biomedical Engineering ShanghaiTech University Shanghai China Department of Research and Development Shanghai United Imaging Intelligence Co. Ltd. Shanghai China Department of Artificial Intelligence Korea University Seoul Korea Republic of

Accurate segmentation of brain tumors from multi-modal Magnetic Resonance (MR) images is essential in brain tumor diagnosis and treatment. However, due to the existence of domain shifts among different modalities, the performance of networks decreases dramatically when training on one modality and performing on another, e.g., train on T1 image while perform on T2 image, which is often required in clinical applications. This also prohibits a network from being trained on labeled data and then transferred to unlabeled data from a different domain. To overcome this, unsupervised domain adaptation (UDA) methods provide effective solutions to alleviate the domain shift between labeled source data and unlabeled target data. In this paper, we propose a novel Bidirectional Global-to-Local (BiGL) adaptation framework under an UDA scheme. Specifically, A bidirectional image synthesis and segmentation module is proposed to segment the brain tumor using the intermediate data distributions generated for the two domains, which includes an image-to-image translator and a shared-weighted segmentation network. Further, a global-to-local consistency learning module is proposed to build robust representation alignments in an integrated way. Extensive experiments on a multi-modal brain MR benchmark dataset demonstrate that the proposed method outperforms several state-of-the-art unsupervised domain adaptation methods by a large margin, while a comprehensive ablation study validates the effectiveness of each key component. The implementation code of our method will be released at https://***/KeleiHe/BiGL. © 2021, CC BY-NC-SA.

关键词： Generative adversarial networks

Towards artificial general intelligence via a multimodal foundation model

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Fei, Nanyi Lu, Zhiwu Gao, Yizhao Yang, Guoxing Huo, Yuqi Wen, Jingyuan Lu, Haoyu Song, Ruihua Gao, Xin Xiang, Tao Sun, Hao Wen, Ji-Rong Gaoling School of Artificial Intelligence Renmin University of China Beijing China Beijing Key Laboratory of Big Data Management and Analysis Methods Beijing China School of Information Renmin University of China Beijing China Computer Electrical and Mathematical Sciences and Engineering Division King Abdullah University of Science and Technology Thuwal Saudi Arabia Department of Electrical and Electronic Engineering University of Surrey Guildford United Kingdom

The fundamental goal of artificial intelligence (AI) is to mimic the core cognitive activities of human. Despite tremendous success in the AI research, most of existing methods have only single-cognitive ability. To overcome this limitation and take a solid step towards artificial general intelligence (AGI), we develop a foundation model pre-trained with huge multimodal data, which can be quickly adapted for various downstream cognitive tasks. To achieve this goal, we propose to pre-train our foundation model by self-supervised learning with weak semantic correlation data crawled from the Internet and show that promising results can be obtained on a wide range of downstream tasks. Particularly, with the developed model-interpretability tools, we demonstrate that strong imagination ability is now possessed by our foundation model. We believe that our work makes a transformative stride towards AGI, from our common practice of "weak or narrow AI" to that of "strong or generalized AI". © 2021, CC BY.

关键词： Semantics

Correction to: SleepBoost: a multi‑level tree‑based ensemble model for automatic sleep stage classification

学校读者我要写书评

暂无评论

Medical & biological engineering & computing 2024年第9期62卷 2785页

作者： Akib Zaman Shiu Kumar Swakkhar Shatabda Iman Dehzangi Alok Sharma Computer Science and Artificial Intelligence Laboratory (CSAIL) Electrical Engineering and Computer Science Department Massachusetts Institute of Technology Cambridge MA USA. School of Electrical & Electronics Engineering Fiji National University Suva Fiji. shiu.kumar@fnu.ac.fj. Centre for Artificial Intelligence and Robotics (CAIR) United International University Dhaka Bangladesh. Department of Computer Science Rutgers University Camden NJ USA. Center for Computational and Integrative Biology Rutgers University Camden USA. Laboratory for Medical Science Mathematics RIKEN Center for Integrative Medical Sciences Yokohama 230‑0045 Japan. Institute for Integrated and Intelligent Systems Griffith University Nathan Brisbane QLD Australia.

DeePMD-kit v3: A Multiple-Backend Framework for Machine Learning Potentials

学校读者我要写书评

暂无评论

arXiv 2025年

作者： Zeng, Jinzhe Zhang, Duo Peng, Anyang Zhang, Xiangyu He, Sensen Wang, Yan Liu, Xinzijian Bi, Hangrui Li, Yifan Cai, Chun Zhang, Chengqian Du, Yiming Zhu, Jia-Xin Mo, Pinghui Huang, Zhengtao Zeng, Qiyu Shi, Shaochen Qin, Xuejian Yu, Zhaoxi Luo, Chenxing Ding, Ye Liu, Yun-Pei Shi, Ruosong Wang, Zhenyu Bore, Sigbjørn Løland Chang, Junhan Deng, Zhe Ding, Zhaohan Han, Siyuan Jiang, Wanrun Ke, Guolin Liu, Zhaoqing Lu, Denghui Muraoka, Koki Oliaei, Hananeh Singh, Anurag Kumar Que, Haohui Xu, Weihong Xu, Zhangmancang Zhuang, Yong-Bin Dai, Jiayu Giese, Timothy J. Jia, Weile Xu, Ben York, Darrin M. Zhang, Linfeng Wang, Han School of Artificial Intelligence and Data Science Unversity of Science and Technology of China Hefei China AI for Science Institute Beijing100080 China DP Technology Beijing100080 China Academy for Advanced Interdisciplinary Studies Peking University Beijing100871 China State Key Lab of Processors Institute of Computing Technology Chinese Academy of Sciences Beijing100871 China University of Chinese Academy of Sciences Beijing China Baidu Inc. Beijing China Department of Computer Science University of Toronto TorontoON Canada Department of Chemistry Princeton University PrincetonNJ08540 United States University of Chinese Academy of Sciences Beijing100871 China State Key Laboratory of Physical Chemistry of Solid Surfaces iChEM College of Chemistry and Chemical Engineering Xiamen University Xiamen361005 China College of Integrated Circuits Hunan University Changsha410082 China State Key Laboratory of Advanced Technology for Materials Synthesis and Processing Center for Smart Materials and Device Integration School of Material Science and Engineering Wuhan University of Technology Wuhan430070 China College of Science National University of Defense Technology Changsha410073 China Hunan Key Laboratory of Extreme Matter and Applications National University of Defense Technology Changsha410073 China ByteDance Research Beijing100098 China Ningbo Institute of Materials Technology and Engineering Chinese Academy of Sciences Ningbo315201 China College of Materials Science and Opto-Electronic Technology University of Chinese Academy of Sciences Beijing100049 China Key Laboratory of Theoretical and Computational Photochemistry of Ministry of Education College of Chemistry Beijing Normal University Beijing100875 China Department of Geosciences Princeton University PrincetonNJ08544 United States Department of Applied Physics and Applied Mathematics Columbia University New YorkNY10027 United States IKKEM Fujian Xiamen361005 China Graduate

In recent years, machine learning potentials (MLPs) have become indispensable tools in physics, chemistry, and materials science, driving the development of software packages for molecular dynamics (MD) simulations and related applications. These packages, typically built on specific machine learning frameworks such as TensorFlow, PyTorch, or JAX, face integration challenges when advanced applications demand communication across different frameworks. The previous TensorFlow-based implementation of DeePMD-kit exemplified these limitations. In this work, we introduce DeePMD-kit version 3, a significant update featuring a multi-backend framework that supports TensorFlow, PyTorch, JAX, and PaddlePaddle backends, and demonstrate the versatility of this architecture through the integration of other MLPs packages and of Differentiable Molecular Force Field. This architecture allows seamless backend switching with minimal modifications, enabling users and developers to integrate DeePMD-kit with other packages using different machine learning frameworks. This innovation facilitates the development of more complex and interoperable workflows, paving the way for broader applications of MLPs in scientific research. Copyright © 2025, The Authors. All rights reserved.

关键词： Molecular dynamics