检索结果-内蒙古大学图书馆

41st International Conference on Machine Learning, ICML 2024

作者： Gu, Zhibin Li, Zhendong Feng, Songhe Key Laboratory of Big Data & Artificial Intelligence in Transportation Beijing Jiaotong University Ministry of Education Beijing China School of Computer Science and Technology Beijing Jiaotong University Beijing100044 China

This paper presents an efficient and scalable incomplete multi-view clustering method, referred to as Enhanced Dictionary-Induced tenSorized incomplete multi-view clustering with Gaussian errOr raNk minimization (EDISON). Specifically, EDISON employs an enhanced dictionary representation strategy as the foundation for inferring missing data and constructing anchor graphs, ensuring robustness to less-than-ideal data and maintaining high computational efficiency. Additionally, we introduce Gaussian error rank as a concise approximation of the true tensor rank, facilitating a comprehensive exploration of the diverse information encapsulated by various singular values in tensor data. Furthermore, we integrate a hyper-anchor graph Laplacian manifold regularization into the tensor representation, allowing for the simultaneous utilization of inter-view high-order correlations and intra-view local correlations. Extensive experiments demonstrate the superiority of the EDISON model in both effectiveness and efficiency compared to SOTA methods. Copyright 2024 by the author(s)

关键词： Tensors

来源：评论

学校读者我要写书评

暂无评论

A survey on causal inference for recommendation

引用

The Innovation 2024年第2期5卷 130-144页

作者： Huishi Luo Fuzhen Zhuang Ruobing Xie Hengshu Zhu Deqing Wang Zhulin An Yongjun Xu Institute of Artificial Intelligence Beihang UniversityBeijing 100191China Zhongguancun Laboratory Beijing 100094China WeChat Search Application Department TencentBeijing 100080China The Career Science Laboratory BOSS ZhipinBeijing 100028China SKLSDE School of Computer ScienceBeihang UniversityBeijing 100191China Institute of Computing Technology Chinese Academy of SciencesBeijing 100190China

Causal inference has recently garnered significant interest among recommender system(RS)researchers due to its ability to dissect cause-and-effect relationships and its broad applicability across multiple *** offers a framework to model the causality in RSs such as confounding effects and deal with counterfactual problems such as offline policy evaluation and data *** there are already some valuable surveys on causal recommendations,they typically classify approaches based on the practical issues faced in RS,a classification that may disperse and fragment the uni-fied causal *** RS researchers’unfamiliarity with causality,it is necessary yet challenging to comprehensively review relevant studies from a coherent causal theoretical perspective,thereby facilitating a deeper integration of causal inference in *** survey provides a systematic review of up-to-date papers in this area from a causal theory standpoint and traces the evolutionary development of RS methods within the same causal ***,we introduce the fundamental concepts of causal inference as the basis of the following ***,we propose a novel theory-driven taxonomy,categorizing existing methods based on the causal theory employed,namely those based on the potential outcome framework,the structural causal model,and general *** review then delves into the technical details of how existing methods apply causal inference to address particular recommender ***,we highlight some promising directions for future research in this *** papers and open-source resources will be progressively available at https://***/Chrissie-Law/Causal-Inference-forRecommendation.

关键词： survey details causal

来源：评论

学校读者我要写书评

暂无评论

A Fast Clustering Based Evolutionary Algorithm for Super-Large-Scale Sparse Multi-Objective Optimization

引用

IEEE/CAA Journal of Automatica Sinica 2023年第4期10卷 1048-1063页

作者： Ye Tian Yuandong Feng Xingyi Zhang Changyin Sun Key Laboratory of Intelligent Computing and Signal Processing of Ministry of Education Institutes of Physical Science and Information TechnologyAnhui UniversityHefei 230601China School of Computer Science and Technology Anhui UniversityHefei 230601China School of Artificial Intelligence Anhui UniversityHefei 230601China School of Automation Southeast UniversityNanjing 210096China

During the last three decades,evolutionary algorithms(EAs)have shown superiority in solving complex optimization problems,especially those with multiple objectives and non-differentiable ***,due to the stochastic search strategies,the performance of most EAs deteriorates drastically when handling a large number of decision *** tackle the curse of dimensionality,this work proposes an efficient EA for solving super-large-scale multi-objective optimization problems with sparse optimal *** proposed algorithm estimates the sparse distribution of optimal solutions by optimizing a binary vector for each solution,and provides a fast clustering method to highly reduce the dimensionality of the search *** importantly,all the operations related to the decision variables only contain several matrix calculations,which can be directly accelerated by *** existing EAs are capable of handling fewer than 10000 real variables,the proposed algorithm is verified to be effective in handling 1000000 real ***,since the proposed algorithm handles the large number of variables via accelerated matrix calculations,its runtime can be reduced to less than 10%of the runtime of existing EAs.

关键词： Evolutionary computation fast clustering sparse multi-objective optimization super-large-scale optimization

来源：评论

学校读者我要写书评

暂无评论

Earning Extra Performance From Restrictive Feedbacks

引用

IEEE Transactions on Pattern Analysis and Machine intelligence 2023年第10期45卷 11753-11765页

作者： Li, Jing Pan, Yuangang Lyu, Yueming Yao, Yinghua Sui, Yulei Tsang, Ivor W. 138632 Singapore University of Technology Sydney The Australian Artificial Intelligence Institute UltimoNSW2007 Australia Southern University of Science and Technology The Guangdong Key Laboratory of Brain-inspired Intelligent Computation Department of Computer Science and Engineering Shenzhen518055 China University of New South Wales The School of Computer Science and Engineering Sydney1466 Australia

Many machine learning applications encounter situations where model providers are required to further refine the previously trained model so as to gratify the specific need of local users. This problem is reduced to the standard model tuning paradigm if the target data is permissibly fed to the model. However, it is rather difficult in a wide range of practical cases where target data is not shared with model providers but commonly some evaluations about the model are accessible. In this paper, we formally set up a challenge named Earning eXtra PerformancE from restriCTive feEDdbacks (EXPECTED) to describe this form of model tuning problems. Concretely, EXPECTED admits a model provider to access the operational performance of the candidate model multiple times via feedback from a local user (or a group of users). The goal of the model provider is to eventually deliver a satisfactory model to the local user(s) by utilizing the feedbacks. Unlike existing model tuning methods where the target data is always ready for calculating model gradients, the model providers in EXPECTED only see some feedbacks which could be as simple as scalars, such as inference accuracy or usage rate. To enable tuning in this restrictive circumstance, we propose to characterize the geometry of the model performance with regard to model parameters through exploring the parameters' distribution. In particular, for deep models whose parameters distribute across multiple layers, a more query-efficient algorithm is further tailor-designed that conducts layerwise tuning with more attention to those layers which pay off better. Our theoretical analyses justify the proposed algorithms from the aspects of both efficacy and efficiency. Extensive experiments on different applications demonstrate that our work forges a sound solution to the EXPECTED problem, which establishes the foundation for future studies towards this direction. © 1979-2012 IEEE.

关键词： Efficiency

来源：评论

学校读者我要写书评

暂无评论

SfPUEL: Shape from Polarization under Unknown Environment Light 38

SfPUEL: Shape from Polarization under Unknown Environment Li...

引用

38th Conference on Neural Information Processing Systems, NeurIPS 2024

作者： Lyu, Youwei Guo, Heng Zhang, Kailong Li, Si Shi, Boxin School of Artificial Intelligence Beijing University of Posts and Telecommunications China State Key Laboratory for Multimedia Information Processing School of Computer Science Peking University China National Engineering Research Center of Visual Technology School of Computer Science Peking University China

Shape from polarization (SfP) benefits from advancements like polarization cameras for single-shot normal estimation, but its performance heavily relies on light conditions. This paper proposes SfPUEL, an end-to-end SfP method to jointly estimate surface normal and material under unknown environment light. To handle this challenging light condition, we design a transformer-based framework for enhancing the perception of global context features. We further propose to integrate photometric stereo (PS) priors from pretrained models to enrich extracted features for high-quality normal predictions. As metallic and dielectric materials exhibit different BRDFs, SfPUEL additionally predicts dielectric and metallic material segmentation to further boost performance. Experimental results on synthetic and our collected real-world dataset demonstrate that SfPUEL significantly outperforms existing SfP and single-shot normal estimation methods. The code and dataset is available at https://***/YouweiLyu/SfPUEL. © 2024 Neural information processing systems foundation. All rights reserved.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Deep Modeling and Optimization of Medical Image Classification 22

Deep Modeling and Optimization of Medical Image Classificati...

引用

22nd IEEE International Symposium on Biomedical Imaging, ISBI 2025

作者： Wu, Yihang Owais, Muhammad Kateb, Reem Chaddad, Ahmad College of Computer Science and Engineering Jeddah University Jeddah Saudi Arabia School of Artificial Intelligence Guilin University of Electronic Technology Aipm China Laboratory for Imagery Vision and Artificial Intelligence Ècole de Technologie Supérieure Canada

ISBN: (纸本)9798331520526

Deep models, such as convolutional neural networks (CNNs) and vision transformer (ViT), demonstrate remarkable performance in image classification. However, those deep models require large data to fine-tune, which is impractical in the medical domain due to the data privacy issue. Furthermore, despite the feasible performance of contrastive language image pre-training (CLIP) in the natural domain, the potential of CLIP has not been fully investigated in the medical field. To face these challenges, we considered three scenarios: 1) we introduce a novel CLIP variant using four CNNs and eight ViTs as image encoders for the classification of brain cancer and skin cancer, 2) we combine 12 deep models with two federated learning techniques to protect data privacy, and 3) we involve traditional machine learning (ML) methods to improve the generalization ability of those deep models in unseen domain data. The experimental results indicate that maxvit shows the highest averaged (AVG) test metrics (AVG = 87.03%) in HAM10000 dataset with multimodal learning, while convnext-1 demonstrates remarkable test with an F1-score of 83.98% compared to swin-b with 81.33% in FL model. Furthermore, the use of support vector machine (SVM) can improve the overall test metrics with AVG of 2% for swin transformer series in ISIC2018. Our codes are available at https://***/AIPMLab/SkinCancerSimulation. © 2025 IEEE.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

LGMD-based Neural Network for Detecting Abnormal Velocity Targets in Moving Crowd 9

LGMD-based Neural Network for Detecting Abnormal Velocity Ta...

引用

9th International Symposium on computer and Information Processing Technology, ISCIPT 2024

作者： Zhao, Zhongxiang Hu, Bin Guizhou University State Key Laboratory of Public Big Data College of Computer Science and Technology Guiyang550025 China Guizhou University College of Computer Science & Technology Department of Computer Science Guiyang550025 China Artificial Intelligence Research Institute of Guizhou University Guizhou University Guiyang550025 China

ISBN: (纸本)9798350388404

Detecting abnormal velocity targets is critical especially in public surveillance for crowd activity monitoring. Although there are some explorations on one such issue, traditional methods still perform poorly in complex scenes. In this paper, a novel visual neural network is investigated to perceive abnormal velocity targets in moving crowd, based on the latest neurophysiological achievements revealed in locusts' vision systems. The proposed neural network contains two neural counterparts, i.e., the presynaptic and the postsynaptic networks. The former one receives visual signals and processes them to capture the motion cues of different targets, and the latter one filters the salience energies to perceive abnormal velocity targets in the field of view. Numerical experiments carried out show that the proposed neural network can effectively detect abnormal velocity targets in moving crowd. This study is an important step towards dynamic visual information processing in crowd behavior analysis. © 2024 IEEE.

关键词： Visual servoing

来源：评论

学校读者我要写书评

暂无评论

Rational 3D object placement based on deep learning based plane detection

引用

Multimedia Tools and Applications 2023年第28期82卷 44555-44576页

作者： Yang, Wei-Jong Lu, Li-Yu Chan, Din-Yuen Department of Artificial Intelligence and Computer Engineering National Chin-Yi University of Technology Taichung Taiwan Telecommunication Laboratories Chunghwa Telecom Co. Ltd. Internet of Things Laboratory Taoyuan Taiwan Department of Computer Science and Information Engineering National Chiayi University Chiayi Taiwan

Effective acquisition of 3D planar features from a 2D image for immersive AR applications is challenging without any 3D depth information. In this paper, we present a novel planar object placement (POP) system for rational insertion of 3D objects on plane surfaces and fitting their plane orientations in a given 2D image. The POP system is composed of an adaptive edge extractor (AEE), a vanishing point detector (VPD), a rational fitting transformer (RFT) and a plane normal detection network (PNDnet), which performs the estimation of planar features. With the inputs of the color image and the guided edge map retrieved by the AEE, the PNDnet based on a gating weighted U-Net, whose gating weights are controlled by global cross-level connection (GCC) blocks, can properly extract 3D information including planar pixel-wise normal map, semantic plane-segmented map and plane-wise normal vectors. Simultaneously, with plane-wise normal vectors and the VPD-estimated vanishing points, the RFT can easily induce the best placement position for projecting the AR object on a destination plane with better coherent 3D perspectives. Besides, the POP system allows the users to make the subtle tunes of 3D orientation to the inserted object for personal preferences. Experimental results show that the proposed POP system, which successfully guides the 3D-inserted objects to match up the surfaces and orientations of the planes in the target image, will become an effective AR tool for the insertion of 3D objects in target images and videos in the future. © 2023, The Author(s), under exclusive licence to Springer science+Business Media, LLC, part of Springer Nature.

关键词： Semantic Segmentation

来源：评论

学校读者我要写书评

暂无评论

Multi-Agent Vulcan: An Information-Driven Multi-Agent Path Finding Approach

Multi-Agent Vulcan: An Information-Driven Multi-Agent Path F...

引用

IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)

作者： Jake Olkin Viraj Parimi Brian Williams Computer Science and Artificial Intelligence Laboratory Massachusetts Institute of Technology Cambridge MA

ISBN: (数字)9798350377705

ISBN: (纸本)9798350377712

Scientists often search for phenomenon of interest while exploring new environments. Autonomous vehicles are deployed to explore such areas where human-operated vehicles would be costly or dangerous. Online control of autonomous vehicles for information-gathering is called adaptive sampling and can be framed as a Partially Observable Markov Decision Process (POMDPs) that uses information gain as its principal objective. While prior work focuses largely on single-agent scenarios, this paper confronts challenges unique to multi-agent adaptive sampling, such as avoiding redundant observations, preventing vehicle collision, and facilitating path planning under limited communication. We start with Multi-Agent Path Finding (MAPF) methods, which address collision avoidance by decomposing the multi-agent path planning problem into a series of single-agent path planning problems. We present an extension to these methods called information-driven MAPF which addresses multi-agent information gain under limited communication. First, we introduce an admissible heuristic that relaxes mutual information gain to an additive function that can be evaluated as a set of independent single agent path planning problems. Second, we extend our approach to a distributed system that is robust to limited communication. When all agents are in range, the group plans jointly to maximize information. When some agents move out of range, communicating subgroups are formed and the subgroups plan independently. Since redundant observations are less likely when vehicles are far apart, this approach only incurs a small loss in information gain, resulting in an approach that gracefully transitions from full to partial communication. We evaluate our method against other adaptive sampling strategies across various scenarios, including real-world robotic applications. Our method was able to locate up to 200% more unique phenomena in certain scenarios, and each agent located its first unique phenomenon fast

关键词： Additives Markov decision processes Path planning Collision avoidance Autonomous vehicles Mutual information Intelligent robots

来源：评论

学校读者我要写书评

暂无评论

An Approach Based on Knowledge Distillation for Lightweight Defect Classification of Green Plums

IEEE Transactions on AgriFood Electronics

引用

IEEE Transactions on AgriFood Electronics 2025年第1期3卷 213-223页

作者： Wang, Jinhai Wang, Wei Liao, Lan Luo, Lufeng Lin, Xuemin Zeng, Xinan Foshan University School of Computer Science and Artificial Intelligence Foshan528000 China Foshan University Department of Food Science Foshan528000 China Foshan University Guangdong Key Laboratory of Intelligent Food Manufacturing Foshan528225 China Foshan University School of Mechatronic Engineering and Automation Foshan528000 China

During the cultivation and growth of green plums, various defects frequently occur, potentially affecting their overall quality and economic value. Accurate classification and identification of these defects have become essential components of the harvesting process, particularly when employing smart agricultural equipment. These defects pose significant challenges to the yield and quality of green plums, making their precise detection crucial for ensuring optimal output and economic efficiency. However, most contemporary research on fruit defect classification and grading using artificial intelligence techniques primarily focuses on accuracy, often neglecting the constraints imposed by limited resources. This study addresses the aforementioned challenges by employing knowledge distillation techniques to optimize the performance of a lightweight model. Specifically, during the knowledge distillation process, the vision transformer model, known for its robust recognition capabilities, was selected as the teacher model. The lightweight MobileNetv3 model, chosen for its ease of deployment, served as the student model and was trained using the Lion optimizer. In addition, the dual guidance learning module was designed to enhance knowledge transfer between the teacher and student models, thereby improving the overall capability of the student model. Experimental validation demonstrated that the proposed method excels in the green plum defect recognition task, with the student model, MobileNetv3, achieving an accuracy of 99.17% and exhibiting high performance in key metrics such as precision, recall, and F1-score. Notably, MobileNetv3 not only delivers exceptional performance but also features a low parameter count and computational complexity, facilitating its efficient deployment in practical applications. This study provides an effective and practical solution for the automatic identification and sorting of green plum defects, significantly advancing the development an

关键词： Teaching

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：