检索结果-内蒙古大学图书馆

Proceedings of the 37th International Conference on Neural information processing Systems

作者： Shizhe Ding Boyang Xia Dongbo Bu Key Laboratory of Intelligent Information Processing Institute of Computing Technology Chinese Academy of Sciences Beijing China and University of Chinese Academy of Sciences Beijing China Key Laboratory of Intelligent Information Processing Institute of Computing Technology Chinese Academy of Sciences Beijing China and University of Chinese Academy of Sciences Beijing China and Central China Institute for Artificial Intelligence Technologies Zhengzhou China

Accurate interpolation algorithms are highly desired in various theoretical and engineering scenarios. Unlike the traditional numerical algorithms that have exact zero-residual constraints on observed points, the neural network-based interpolation methods exhibit non-zero residuals at these points. These residuals, which provide observations of an underlying residual function, can guide predicting interpolation functions, but have not been exploited by the existing approaches. To fill this gap, we propose Hierarchical INTerpolation Network (HINT), which utilizes the residuals on observed points to guide target function estimation in a hierarchical fashion. HINT consists of several sequentially arranged lightweight interpolation blocks. The first interpolation block estimates the main component of the target function, while subsequent blocks predict the residual components using observed points residuals of the preceding blocks. The main component and residual components are accumulated to form the final interpolation results. Furthermore, under the assumption that finer residual prediction requires a more focused attention range on observed points, we utilize hierarchical local constraints in correlation modeling between observed and target points. Extensive experiments demonstrate that HINT outperforms existing interpolation algorithms significantly in terms of interpolation accuracy across a wide variety of datasets, which underscores its potential for practical scenarios.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Meta Ordinal Regression Forest for Medical Image Classification With Ordinal Labels

引用

IEEE/CAA Journal of Automatica Sinica 2022年第7期9卷 1233-1247页

作者： Yiming Lei Haiping Zhu Junping Zhang Hongming Shan Shanghai Key Laboratory of Intelligent Information Processing the School of Computer ScienceFudan UniversityShanghai 200433China with Huawei Shanghai 200120China Institute of Science and Technology for Brain-Inspired Intelligence and MOE Frontiers Center for Brain Science Fudan UniversityShanghai 200433 Shanghai Center for Brain Science and Brain-Inspired Technology Shanghai 200031China IEEE

The performance of medical image classification has been enhanced by deep convolutional neural networks(CNNs),which are typically trained with cross-entropy(CE)***,when the label presents an intrinsic ordinal property in nature,e.g.,the development from benign to malignant tumor,CE loss cannot take into account such ordinal information to allow for better *** improve model generalization with ordinal information,we propose a novel meta ordinal regression forest(MORF)method for medical image classification with ordinal labels,which learns the ordinal relationship through the combination of convolutional neural network and differential forest in a meta-learning *** merits of the proposed MORF come from the following two components:A tree-wise weighting net(TWW-Net)and a grouped feature selection(GFS)***,the TWW-Net assigns each tree in the forest with a specific weight that is mapped from the classification loss of the corresponding ***,all the trees possess varying weights,which is helpful for alleviating the tree-wise prediction ***,the GFS module enables a dynamic forest rather than a fixed one that was previously used,allowing for random feature *** training,we alternatively optimize the parameters of the CNN backbone and TWW-Net in the meta-learning framework through calculating the Hessian *** results on two medical image classification datasets with ordinal labels,i.e.,LIDC-IDRI and Breast Ultrasound datasets,demonstrate the superior performances of our MORF method over existing state-of-the-art methods.

关键词： Terms-Convolutional neural network(CNNs) medical image classification meta-learning ordinal regression random forest

来源：评论

学校读者我要写书评

暂无评论

A SAR Target Recognition Strategy Guided by Electromagnetic Scattering Feature

A SAR Target Recognition Strategy Guided by Electromagnetic ...

引用

Signal, information and Data processing (ICSIDP), IEEE International Conference on

作者： Yifei Yin Liang Chen Lujiao Liu Yufan Meng Fan Chen Hao Shi Beijing Institute of Technology National Key Laboratory of Science and Technology on Space-Born Intelligent Information Processing Beijing China Aerospace Information Research Institute Chinese Academy of Sciences Beijing China

ISBN: (数字)9798331515669

ISBN: (纸本)9798331515676

SAR target Automatic Target Recognition (ATR) is indispensable in SAR image interpretation. Recently, deep learning technology has been widely used in SAR target recognition tasks. Most networks achieve incremental improvements in target recognition by modifying their structures to extract visual features of targets. However, due to the unique imaging mechanism, relying solely on visual features often leads to the loss of target information. In contrast, the ASC model, which captures the electromagnetic scattering characteristics of the target, plays a crucial role in target recognition tasks. Unfortunately, traditional parameter estimation methods for extracting the ASC model are computationally expensive and time-consuming, making them impractical for real-world applications. To address these issues, we propose a novel target recognition method based on electromagnetic scattering features in this paper. First, a lightweight network-based feature extraction module is designed. Then, the target ASC image is used as the ground truth for guidance, with image intensity and target structure serving as the loss functions during training. Finally, an ASC model-guided feature fusion network is designed, utilizing the fused features for target recognition. On the MSTAR dataset, a visual assessment experiment demonstrated that the proposed feature extraction module effectively extracts electromagnetic scattering features under various operating conditions. Subsequently, in downstream classification tasks, the inclusion of the proposed module resulted in improved accuracy compared to other networks. Additionally, a visualization analysis of the classification network showed that, under the guidance of electromagnetic scattering features, the network achieved good interpretability.

关键词： Training Deep learning Visualization Parameter estimation Target recognition Computational modeling Electromagnetic scattering Imaging Feature extraction Radar polarimetry

来源：评论

学校读者我要写书评

暂无评论

A Brief Overview of ChatGPT:The History,Status Quo and Potential Future Development

引用

IEEE/CAA Journal of Automatica Sinica 2023年第5期10卷 1122-1136页

作者： Tianyu Wu Shizhu He Jingping Liu Siqi Sun Kang Liu Qing-Long Han Yang Tang the Key Laboratory of Smart Manufacturing in Energy Chemical Process East China University of Science and TechnologyShanghai 200237China the Laboratory of Cognition and Decision Intelligence for Complex Systems Institute of AutomationChinese Academy of SciencesBeijing 100190 the School of Artificial Intelligence University of Chinese Academy of SciencesBeijing 100049China the School of Information Science and Engineering East China University of Science and TechnologyShanghai 200237China the Research Institute of Intelligent Complex Systems Fudan UniversityShanghai 200437China the School of Science Computing and Engineering TechnologiesSwinburne University of TechnologyMelbourne VIC 3122Australia

ChatG PT,an artificial intelligence generated content (AIGC) model developed by OpenAI,has attracted worldwide attention for its capability of dealing with challenging language understanding and generation tasks in the form of *** paper briefly provides an overview on the history,status quo and potential future development of ChatGPT,helping to provide an entry point to think about ***,from the limited open-accessed resources,we conclude the core techniques of ChatGPT,mainly including large-scale language models,in-context learning,reinforcement learning from human feedback and the key technical steps for developing *** further analyze the pros and cons of ChatGPT and we rethink the duality of ChatGPT in various *** it has been widely acknowledged that ChatGPT brings plenty of opportunities for various fields,mankind should still treat and use ChatG PT properly to avoid the potential threat,e.g.,academic integrity and safety ***,we discuss several open problems as the potential development of ChatGPT.

关键词： AIGC ChatGPT GPT-3 GPT-4 human feedback large language models

来源：评论

学校读者我要写书评

暂无评论

NAS-HR:Neural architecture search for heart rate estimation from face videos

引用

Virtual Reality & intelligent Hardware 2021年第1期3卷 33-42页

作者： Hao LU Hu HAN School of Artificial Intelligence University of Chinese Academy of SciencesBeijing 100049China Key Laboratory of Intelligent Information Processing Chinese Academy of Sciences(CAS)Institute of Computing TechnologyBeijing 100080China Peng Cheng Laboratory Shenzhen 518000China

Background In anticipation of its great potential application to natural human-computer interaction and health monitoring,heart-rate(HR)estimation based on remote photoplethysmography has recently attracted increasing research *** the recent deep-learning-based HR estimation methods have achieved promising performance,their computational costs remain high,particularly in mobile-computing *** We propose a neural architecture search approach for HR estimation to automatically search a lightweight network that can achieve even higher accuracy than a complex network while reducing the computational ***,we define the regions of interests based on face landmarks and then extract the raw temporal pulse signals from the R,G,and B channels in each ***,pulse-related signals are extracted using a plane-orthogonal-to-skin algorithm,which are combined with the R and G channel signals to create a spatial-temporal ***,a differentiable architecture search approach is used for the network-structure *** Compared with the state-of-the-art methods on the public-domain VIPL-HR and PURE databases,our method achieves better HR estimation performance in terms of several evaluation metrics while requiring a much lower computational cost1.

关键词： Heart-rate estimation Plane-orthogonal-to-skin STMap Differentiable architecture search

来源：评论

学校读者我要写书评

暂无评论

FoodSky: A Food-oriented Large Language Model that Passes the Chef and Dietetic Examination

arXiv

引用

arXiv 2024年

作者： Zhou, Pengfei Min, Weiqing Fu, Chaoran Jin, Ying Huang, Mingyu Li, Xiangyang Mei, Shuhuan Jiang, Shuqiang The Key Laboratory of Intelligent Information Processing Institute of Computing Technology Chinese Academy of Sciences Beijing100190 China The University of Chinese Academy of Sciences Beijing100049 China The Institute of Intelligent Computing Technology Chinese Academy of Sciences Suzhou215124 China Technology Co. Ltd. Suzhou215024 China

Food is foundational to human life, serving not only as a source of nourishment but also as a cornerstone of cultural identity and social interaction. As the complexity of global dietary needs and preferences grows, food intelligence is needed to enable food perception and reasoning for various tasks, ranging from recipe generation and dietary recommendation to diet-disease correlation discovery and understanding. Towards this goal, for powerful capabilities across various domains and tasks in Large Language Models (LLMs), we introduce Food-oriented LLM FoodSky to comprehend food data through perception and reasoning. Considering the complexity and typicality of Chinese cuisine, we first construct one comprehensive Chinese food corpus FoodEarth from various authoritative sources, which can be leveraged by FoodSky to achieve deep understanding of food-related data. We then propose Topic-based Selective State Space Model (TS3M) and the Hierarchical Topic Retrieval Augmented Generation (HTRAG) mechanism to enhance FoodSky in capturing fine-grained food semantics and generating context-aware food-relevant text, respectively. Our extensive evaluations demonstrate that FoodSky significantly outperforms general-purpose LLMs in both chef and dietetic examinations, with an accuracy of 67.2% and 66.4% on the Chinese National Chef Exam and the National Dietetic Exam, respectively. FoodSky not only promises to enhance culinary creativity and promote healthier eating patterns, but also sets a new standard for domain-specific LLMs that address complex real-world issues in the food domain. An online demonstration of FoodSky is available at http://222.92.101.211:8200. Copyright © 2024, The Authors. All rights reserved.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

Highly isolated two-elements ultra-wideband mimo fractal antenna with multi band-notched characteristics

引用

Progress In Electromagnetics Research C 2021年 116卷 13-24页

作者： Cai, Yong Cheng, Guangshang Ren, Xingang Wu, Jie Ren, Hao Song, Kaihong Huang, Zhixiang Wu, Xianliang Information Materials and Intelligent Sensing Laboratory of Anhui Province Institute of Physical Science and Information Technology Anhui University Hefei230039 China Anhui Province Key Laboratory of Target Recognition and Feature Extraction Luan237000 China Key Laboratory of Intelligent Computing & Signal Processing Ministry of Education Institute of Physical Science and Information Technology Anhui University Hefei230039 China Key Laboratory of Electromagnetic Environmental Sensing Department of Education of Anhui Province Anhui University Hefei230039 China

This work presents a high isolation UWB-MIMO antenna with a bandwidth up to 8.6 GHz based on a Minkowski fractal structure. The proposed antenna is fed by microstrip and comprises two orthogonal monopole antennas, which delivers a decent isolation effect. Moreover, the ground is designed as two separated blocks with an I-shaped branch for improving the isolation degree between the units. The resultant isolation degree of this antenna is greater than 25 dB. Besides, the electromagnetic interference in the partial frequency band (such as Wi-Max band (3.45–4.45 GHz), WLAN band (5.1– 5.8 GHz), and X-band (7.25–7.75 GHz)) is further prevented through etching a split-ring resonator (SRR) and C-slot on the unit. The antenna reflection coefficient of the UWB-MIMO antenna at the notch is 3.5 dB, which indicates that the antenna has a conspicuousness anti-interference effect. Through the above judicious design, the proposed UWB-MIMO antenna possesses a relative bandwidth of 113% (up to 8.6 GHz). The envelope correlation coefficient between antenna units is less than 0.005, and the antenna radiation efficiency is up to 80%. The results indicate that the proposed MIMO antenna meets UWB applications. © 2021, Electromagnetics Academy. All rights reserved.

关键词： Monopole antennas

来源：评论

学校读者我要写书评

暂无评论

Black⁃box adversarial attacks with imperceptible fake user profiles for recommender systems

引用

南京大学学报(自然科学版) 2024年第6期60卷 881-899页

作者： Qian Fulan Liu Jinggang Chen Hai Chen Wenbin Zhao Shu Zhang Yanping Artificial Intelligence Institute Anhui UniversityHefei230601China Key Laboratory of Intelligent Computing and Signal Processing Ministry of EducationAnhui UniversityHefei230601China Information Materials and Intelligent Sensing Laboratory of Anhui Province Anhui UniversityHefei230601China

Attackers inject the designed adversarial sample into the target recommendation system to achieve illegal goals,seriously affecting the security and reliability of the recommendation *** is difficult for attackers to obtain detailed knowledge of the target model in actual scenarios,so using gradient optimization to generate adversarial samples in the local surrogate model has become an effective black‐box attack ***,these methods suffer from gradients falling into local minima,limiting the transferability of the adversarial *** reduces the attack's effectiveness and often ignores the imperceptibility of the generated adversarial *** address these challenges,we propose a novel attack algorithm called PGMRS‐KL that combines pre‐gradient‐guided momentum gradient optimization strategy and fake user generation constrained by Kullback‐Leibler ***,the algorithm combines the accumulated gradient direction with the previous step's gradient direction to iteratively update the adversarial *** uses KL loss to minimize the distribution distance between fake and real user data,achieving high transferability and imperceptibility of the adversarial *** results demonstrate the superiority of our approach over state‐of‐the‐art gradient‐based attack algorithms in terms of attack transferability and the generation of imperceptible fake user data.

关键词： recommendation systems adversarial examples transferability imperceptible

来源：评论

学校读者我要写书评

暂无评论

Size-Invariance Matters: Rethinking Metrics and Losses for Imbalanced Multi-object Salient Object Detection 41

Size-Invariance Matters: Rethinking Metrics and Losses for I...

引用

41st International Conference on Machine Learning, ICML 2024

作者： Li, Feiran Xu, Qianqian Bao, Shilong Yang, Zhiyong Cong, Runmin Cao, Xiaochun Huang, Qingming Institute of Information Engineering Chinese Academy of Sciences Beijing China School of Cyber Security University of Chinese Academy of Sciences Beijing China Key Laboratory of Intelligent Information Processing Institute of Computing Technology Chinese Academy of Sciences Beijing China School of Computer Science and Technology University of Chinese Academy of Sciences Beijing China Institute of Information Science Beijing Jiaotong University Beijing China School of Control Science and Engineering Shandong University Jinan China Key Laboratory of Machine Intelligence and System Control Ministry of Education Jinan China School of Cyber Science and Tech. Sun Yat-sen University Shenzhen Campus China Key Laboratory of Big Data Mining and Knowledge Management Chinese Academy of Sciences Beijing China

This paper explores the size-invariance of evaluation metrics in Salient Object Detection (SOD), especially when multiple targets of diverse sizes co-exist in the same image. We observe that current metrics are size-sensitive, where larger objects are focused, and smaller ones tend to be ignored. We argue that the evaluation should be size-invariant because bias based on size is unjustified without additional semantic information. In pursuit of this, we propose a generic approach that evaluates each salient object separately and then combines the results, effectively alleviating the imbalance. We further develop an optimization framework tailored to this goal, achieving considerable improvements in detecting objects of different sizes. Theoretically, we provide evidence supporting the validity of our new metrics and present the generalization analysis of SOD. Extensive experiments demonstrate the effectiveness of our method. The code is available at https://***/Ferry-Li/SI-SOD. Copyright 2024 by the author(s)

关键词： Object detection

来源：评论

学校读者我要写书评

暂无评论

Domain-Invariant Similarity Activation Map Contrastive Learning for Retrieval-Based Long-Term Visual Localization

引用

IEEE/CAA Journal of Automatica Sinica 2022年第2期9卷 313-328页

作者： Hanjiang Hu Hesheng Wang Zhe Liu Weidong Chen Department of Automation Shanghai Jiao Tong UniversityShanghai 200240China IEEE Department of Automation Institute of Medical RoboticsKey Laboratory of System Control and Information Processing of Ministry of EducationKey Laboratory of Marine Intelligent Equipment and System of Ministry of EducationShanghai Jiao Tong UniversityShanghai 200240China Department of Computer Science and Technology University of CambridgeCambridge CB30FDUnited Kingdom

Visual localization is a crucial component in the application of mobile robot and autonomous *** retrieval is an efficient and effective technique in image-based localization *** to the drastic variability of environmental conditions,e.g.,illumination changes,retrievalbased visual localization is severely affected and becomes a challenging *** this work,a general architecture is first formulated probabilistically to extract domain-invariant features through multi-domain image ***,a novel gradientweighted similarity activation mapping loss(Grad-SAM)is incorporated for finer localization with high *** also propose a new adaptive triplet loss to boost the contrastive learning of the embedding in a self-supervised *** final coarse-to-fine image retrieval pipeline is implemented as the sequential combination of models with and without Grad-SAM *** experiments have been conducted to validate the effectiveness of the proposed approach on the CMU-Seasons *** strong generalization ability of our approach is verified with the RobotCar dataset using models pre-trained on urban parts of the CMU-Seasons *** performance is on par with or even outperforms the state-of-the-art image-based localization baselines in medium or high precision,especially under challenging environments with illumination variance,vegetation,and night-time ***,real-site experiments have been conducted to validate the efficiency and effectiveness of the coarse-to-fine strategy for localization.

关键词： Deep representation learning place recognition visual localization

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：