检索结果-内蒙古大学图书馆

Smart World Congress (SWC), IEEE

作者： Lu Shi Qi Cao Guoqing Zhang Jin Yi Yansen Huang Yigang Cen State Key Laboratory of Advanced Rail Autonomous Operation the School of Computer Science and Technology and Visual Intellgence +X International Cooperation Joint Laboratory of MOE Beijing Jiaotong University Beijing China the School of Computing Science University of Glasgow Singapore With the Key Laboratory of Big Data & Artificial Intelligence in Transportation Ministry of Education the State Key Laboratory of Advanced Rail Autonomous Operation and the School of Computer and Information Technology Beijing Jiaotong University Beijing China the College of Civil Engineering Guizhou University Guizhou Lianjian Civil Engineering Quality Testing Monitoring Center Co. LTD Guizhou China

ISBN: (数字)9798331520861

ISBN: (纸本)9798331520878

While deep learning has significantly advanced point cloud analysis, extracting effective features from their disordered structure remains challenging. Existing approaches often rely on complex network architectures or manual feature engineering to achieve rotation invariance, which increases inference latency. This paper offers a novel perspective on this challenge, showing that rotation-sensitive models can achieve performance comparable to rotation-invariant models when trained with rotation-augmented data. Given the significant differences in the feature distributions of rotation-sensitive and rotation-invariant models, we propose Feature Rotation Invariance Learning (FRIL), a framework that leverages Distance Metric Learning and rotation-based constraints to help rotation-sensitive models extract rotation-invariant features. This approach eliminates the need for additional modules, enabling robust performance against rotations. Extensive experiments demonstrate that FRIL consistently outperforms existing rotation-invariant methods across various visual tasks.

关键词： Point cloud compression Representation learning Analytical models Solid modeling visualization Three-dimensional displays Semantics Cloning Feature extraction Data models

来源：评论

学校读者我要写书评

暂无评论

Next-Future: Sample-Efficient Policy Learning for Robotic-Arm Tasks

arXiv

引用

arXiv 2025年

作者： Özgür, Fikrican Zurbrügg, René Kumar, Suryansh ETH Zürich Switzerland RSL Group ETH Zürich Switzerland Visual Computing and Computational Media Section College of PVFA Department of Electric and Computer Engineering Department of Computer Science and Engineering Texas A&M University College StationTX United States

Hindsight Experience Replay (HER) is widely regarded as the state-of-the-art algorithm for achieving sample-efficient multi-goal reinforcement learning (RL) in robotic manipulation tasks with binary rewards. HER facilitates learning from failed attempts by replaying trajectories with redefined goals. However, it relies on a heuristic-based replay method that lacks a principled framework. To address this limitation, we introduce a novel replay strategy, "Next-Future", which focuses on rewarding single-step transitions. This approach significantly enhances sample efficiency and accuracy in learning multi-goal Markov decision processes (MDPs), particularly under stringent accuracy requirements—a critical aspect for performing complex and precise robotic-arm tasks. We demonstrate the efficacy of our method by highlighting how single-step learning enables improved value approximation within the multi-goal RL framework. The performance of the proposed replay strategy is evaluated across eight challenging robotic manipulation tasks, using ten random seeds for training. Our results indicate substantial improvements in sample efficiency for seven out of eight tasks and higher success rates in six tasks. Furthermore, real-world experiments validate the practical feasibility of the learned policies, demonstrating the potential of "Next-Future" in solving complex robotic-arm tasks. Copyright © 2025, The Authors. All rights reserved.

关键词： Robotic arms

来源：评论

学校读者我要写书评

暂无评论

Global-Supervised Contrastive Loss and View-Aware-Based Post-Processing for Vehicle Re-Identification

arXiv

引用

arXiv 2022年

作者： Hu, Zhijun Xu, Yong Wen, Jie Cheng, Xianjing Zhang, Zaijun Sun, Lilei Wang, Yaowei School of Mathematics and Statistics Guangxi Normal University Guilin541004 China College of Computer Science and Technology Guizhou University Guiyang550025 China Shenzhen Key Laboratory of Visual Object Detection and Recognition Shenzhen China College of Computer Science and Technology Guizhou University Guiyang550025 China Key Laboratory of Complex Systems and Intelligent Computing School of Mathematics and Statistics Qiannan Normal University for Nationalities Duyun558000 China Peng Cheng Laboratory Shenzhen518055 China

In this paper, we propose a Global-Supervised Contrastive loss (LGSupCon) and a view-aware-based post-processing (VABPP) method for the field of vehicle re-identification. The traditional supervised contrastive loss (LSupCon) calculates the distances of features within the batch, so it has the local attribute. While the proposed LGSupCon has new properties and has good global attributes, the positive and negative features of each anchor in the training process come from the entire training set. The proposed VABPP method is the first time that the view-aware-based method is used as a post-processing method in the field of vehicle re-identification. The advantages of VABPP are that, first, it is only used during testing and does not affect the training process. Second, as a post-processing method, it can be easily integrated into other trained re-id models. We directly apply the view-pair distance scaling coefficient matrix calculated by the model trained in this paper to another trained re-id model, and the VABPP method greatly improves its performance, which verifies the feasibility of the VABPP method. © 2022, CC BY-NC-SA.

关键词： Vehicles

来源：评论

学校读者我要写书评

暂无评论

A Novel Smartphone Recommendation System Using Ensemble Machine Learning

A Novel Smartphone Recommendation System Using Ensemble Mach...

引用

computer science and Data Engineering (CSDE), IEEE Asia-Pacific Conference on

作者： Ahmad Almadhor Sidra Abbas Gabriel Avelino Sampedro Mideth Abisado Thippa Reddy Gadekallu College of Computer and Information Sciences Jouf University Sakaka Saudi Arabia Department of Computer Science COMSATS University Islamabad Islamabad Pakistan Faculty of Information and Communication Studies University of the Philippines Open University Los Baños Philippines Center for Computational Imaging and Visual Innovations De La Salle University Manila Philippines College of Computing and Information Technologies National University Manila Philippines Zhongda Group Jiaxing City Zhejiang Province China Department of Electrical and Computer Engineering Lebanese American University Byblos Lebanon School of Information Technology and Engineering Vellore Institute of Technology Tamil Nadu India College of Information Science and Engineering Jiaxing University Jiaxing China Division of Research and Development Lovely Professional University Phagwara India

Due to the proliferation of internet evaluations brought on by the rising demand for smartphones, consumers find it challenging to make accurate selections when purchasing. In this paper, we offer ensemble voting methods based on TF-IDF (Term Frequency-Inverse Document Frequency) features for clas-sifying mobile phone ratings. We use a recently assembled dataset comprising over 13,000 smartphone reviews from the Flipkart website. The suggested approach includes feature extraction using the TF-IDF, data cleaning, balancing, and voting-based model prediction. To identify the recently created Flipkart dataset, the suggested method created an ensemble voting mechanism based on machine learning techniques. According to the experimental findings, the suggested method performs more accurately and efficiently than conventional machine learning techniques. At 98.0 %, the model achieved the greatest accuracy. The suggested method can be expanded to additional e-commerce platforms with sizable datasets of online evaluations and assist customers in making updated purchase preferences.

关键词：

来源：评论

学校读者我要写书评

暂无评论

A Non-Asymptotic Analysis for Stein Variational Gradient Descent

arXiv

引用

arXiv 2020年

作者： Korba, Anna Arbel, Michael Salim, Adil Luise, Giulia Gretton, Arthur Gatsby Computational Neuroscience Unit University College London Visual Computing Center KAUST Computer Science Department University College London

We study the Stein Variational Gradient Descent (SVGD) algorithm, which optimises a set of particles to approximate a target probability distribution π ∝ e−V on Rd. In the population limit, SVGD performs gradient descent in the space of probability distributions on the KL divergence with respect to π, where the gradient is smoothed through a kernel integral operator. In this paper, we provide a novel finite time analysis for the SVGD algorithm. We obtain a descent lemma establishing that the algorithm decreases the objective at each iteration, and provably converges, with less restrictive assumptions on the step size than required in earlier analyses. We further provide a guarantee on the convergence rate in Kullback-Leibler divergence, assuming π satisfies a Stein log-Sobolev inequality as in (Duncan et al., 2019), which takes into account the geometry induced by the smoothed KL gradient. Copyright © 2020, The Authors. All rights reserved.

关键词： Gradient methods

来源：评论

学校读者我要写书评

暂无评论

A non-asymptotic analysis for stein variational gradient descent 20

A non-asymptotic analysis for stein variational gradient des...

引用

Proceedings of the 34th International Conference on Neural Information Processing Systems

作者： Anna Korba Adil Salim Michael Arbel Giulia Luise Arthur Gretton Gatsby Computational Neuroscience Unit University College London Visual Computing Center KAUST Computer Science Department University College London

ISBN: (纸本)9781713829546

We study the Stein Variational Gradient Descent (SVGD) algorithm, which optimises a set of particles to approximate a target probability distribution π ∝ e-V on ℝd. In the population limit, SVGD performs gradient descent in the space of probability distributions on the KL divergence with respect to π, where the gradient is smoothed through a kernel integral operator. In this paper, we provide a novel finite time analysis for the SVGD algorithm. We provide a descent lemma establishing that the algorithm decreases the objective at each iteration, and rates of convergence for the averaged Stein Fisher divergence (also referred to as Kernel Stein Discrepancy). We also provide a convergence result of the finite particle system corresponding to the practical implementation of SVGD to its population version.

关键词：

来源：评论

学校读者我要写书评

暂无评论

The wasserstein proximal gradient algorithm 20

The wasserstein proximal gradient algorithm

引用

Proceedings of the 34th International Conference on Neural Information Processing Systems

作者： Adil Salim Anna Korba Giulia Luise Visual Computing Center KAUST Gatsby Computational Neuroscience Unit University College London Computer Science Department University College London

ISBN: (纸本)9781713829546

Wasserstein gradient flows are continuous time dynamics that define curves of steepest descent to minimize an objective function over the space of probability measures (i.e., the Wasserstein space). This objective is typically a divergence w.r.t. a fixed target distribution. In recent years, these continuous time dynamics have been used to study the convergence of machine learning algorithms aiming at approximating a probability distribution. However, the discrete-time behavior of these algorithms might differ from the continuous time dynamics. Besides, although discretized gradient flows have been proposed in the literature, little is known about their minimization power. In this work, we propose a Forward Backward (FB) discretization scheme that can tackle the case where the objective function is the sum of a smooth and a nonsmooth geodesically convex terms. Using techniques from convex optimization and optimal transport, we analyze the FB scheme as a minimization algorithm on the Wasserstein space. More precisely, we show under mild assumptions that the FB scheme has convergence guarantees similar to the proximal gradient algorithm in Euclidean spaces.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Uncertainty-inspired Open Set Learning for Retinal Anomaly Identification

arXiv

引用

arXiv 2023年

作者： Wang, Meng Lin, Tian Wang, Lianyu Lin, Aidi Zou, Ke Xu, Xinxing Zhou, Yi Peng, Yuanyuan Meng, Qingquan Qian, Yiming Deng, Guoyao Wu, Zhiqun Chen, Junhong Lin, Jianhong Zhang, Mingzhi Zhu, Weifang Zhang, Changqing Zhang, Daoqiang Goh, Rick Siow Mong Liu, Yong Pang, Chi Pui Chen, Xinjian Chen, Haoyu Fu, Huazhu 1 Fusionopolis Way #16-16 Connexis Singapore138632 Singapore Joint Shantou International Eye Center Shantou University the Chinese University of Hong Kong Medical College Shantou University Guangdong515041 China College of Computer Science and Technology Nanjing University of Aeronautics and Astronautics Jiangsu211100 China National Key Laboratory of Fundamental Science on Synthetic Vision the College of Computer Science Sichuan University Sichuan610065 China School of Electronics and Information Engineering Soochow University Jiangsu215006 China School of Biomedical Engineering Anhui Medical University Anhui230032 China Longchuan People’s Hospital Heyuan China Puning People’s Hospital Jieyang China Haifeng PengPai Memory Hospital Shanwei China College of Intelligence and Computing Tianjin University Tianjin300350 China Department of Ophthalmology and Visual Sciences The Chinese University of Hong Kong Hong Kong State Key Laboratory of Radiation Medicine and Protection Soochow University Suzhou215006 China

Failure to recognize samples from the classes unseen during training is a major limitation of artificial intelligence in the real-world implementation for recognition and classification of retinal anomalies. We established an uncertainty-inspired open-set (UIOS) model, which was trained with fundus images of 9 retinal conditions. Besides assessing the probability of each category, UIOS also calculated an uncertainty score to express its confidence. Our UIOS model with thresholding strategy achieved an F1 score of 99.55%, 97.01% and 91.91% for the internal testing set, external target categories (TC)-JSIEC dataset and TC-unseen testing set, respectively, compared to the F1 score of 92.20%, 80.69% and 64.74% by the standard AI model. Furthermore, UIOS correctly predicted high uncertainty scores, which would prompt the need for a manual check in the datasets of non-target categories retinal diseases, low-quality fundus images, and non-fundus images. UIOS provides a robust method for real-world screening of retinal anomalies. © 2023, CC BY.

关键词： Uncertainty analysis

来源：评论

学校读者我要写书评

暂无评论

Large AI Models in Health Informatics: Applications, Challenges, and the Future

arXiv

引用

arXiv 2023年

作者： Qiu, Jianing Li, Lin Sun, Jiankai Peng, Jiachuan Shi, Peilun Zhang, Ruiyang Dong, Yinzhao Lam, Kyle Lo, Frank P.-W. Xiao, Bo Yuan, Wu Wang, Ningli Xu, Dong Lo, Benny The Department of Computing Imperial College London United Kingdom The Department of Biomedical Engineering The Chinese University of Hong Kong Hong Kong Ltd. Hong Kong The Department of Informatics King’s College London United Kingdom The School of Engineering Stanford University United States The Department of Engineering Science University of Oxford United Kingdom The Faculty of Engineering The University of Hong Kong Hong Kong The Department of Surgery and Cancer Imperial College London United Kingdom The Hamlyn Centre for Robotic Surgery Imperial College London United Kingdom Beijing Tongren Eye Center Beijing Tongren Hospital Capital Medical University China Beijing Ophthalmology & Visual Sciences Key Laboratory Beijing China The Department of Electrical Engineering and Computer Science United States The Christopher S. Bond Life Sciences Center University of Missouri United States The Facualty of Medicine Imperial College London United Kingdom

Large AI models, or foundation models, are models recently emerging with massive scales both parameter-wise and data-wise, the magnitudes of which can reach beyond billions. Once pretrained, large AI models demonstrate impressive performance in various downstream tasks. A prime example is ChatGPT, whose capability has compelled people’s imagination about the far-reaching influence that large AI models can have and their potential to transform different domains of our lives. In health informatics, the advent of large AI models has brought new paradigms for the design of methodologies. The scale of multi-modal data in the biomedical and health domain has been ever-expanding especially since the community embraced the era of deep learning, which provides the ground to develop, validate, and advance large AI models for breakthroughs in health-related areas. This article presents a comprehensive review of large AI models, from background to their applications. We identify seven key sectors in which large AI models are applicable and might have substantial influence, including 1) bioinformatics;2) medical diagnosis;3) medical imaging;4) medical © 2023, CC BY-NC-ND.

关键词： Medical imaging

来源：评论

学校读者我要写书评

暂无评论

The wasserstein proximal gradient algorithm

arXiv

引用

arXiv 2020年

作者： Salim, Adil Korba, Anna Luise, Giulia Visual Computing Center KAUST Saudi Arabia Gatsby Computational Neuroscience Unit University College London United Kingdom Computer Science Department University College London United Kingdom

关键词： Convex optimization

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：