检索结果-内蒙古大学图书馆

A survey for light field super-resolution

High-Confidence computing 2024年第1期4卷 118-129页

作者： Mingyuan Zhao Hao Sheng Da Yang Sizhe Wang Ruixuan Cong Zhenglong Cui Rongshan Chen Tun Wang Shuai Wang Yang Huang Jiahao Shen State Key Laboratory of Virtual Reality Technology and Systems School of Computer Science and EngineeringBeihang UniversityBeijing 100191China Key Laboratory of Data Science and Intelligent Computing International Innovation InstituteBeihang UniversityHangzhou 311115China State Key Laboratory of Software Development Environment School of Computer Science and EngineeringBeihang UniversityBeijing 100191China

Compared to 2D imaging data,the 4D light field(LF)data retains richer scene’s structure information,which can significantly improve the computer’s perception capability,including depth estimation,semantic segmentation,and LF ***,there is a contradiction between spatial and angular resolution during the LF image acquisition *** overcome the above problem,researchers have gradually focused on the light field super-resolution(LFSR).In the traditional solutions,researchers achieved the LFSR based on various optimization frameworks,such as Bayesian and Gaussian *** learning-based methods are more popular than conventional methods because they have better performance and more robust generalization *** this paper,the present approach can mainly divided into conventional methods and deep learning-based *** discuss these two branches in light field spatial super-resolution(LFSSR),light field angular super-resolution(LFASR),and light field spatial and angular super-resolution(LFSASR),***,this paper also introduces the primary public datasets and analyzes the performance of the prevalent approaches on these ***,we discuss the potential innovations of the LFSR to propose the progress of our research field.

关键词： Light field super-resolution Convolutional neural network Transformer Sub-aperture image Epipolar-plane image

来源：评论

学校读者我要写书评

暂无评论

An In-depth Investigation of Sparse Rate Reduction in Transformer-like Models

arXiv

引用

arXiv 2024年

作者： Hu, Yunzhe Zou, Difan Xu, Dong School of Computing and Data Science The University of Hong Kong Hong Kong School of Computing and Data Science Institute of Data Science The University of Hong Kong Hong Kong

Deep neural networks have long been criticized for being black-box. To unveil the inner workings of modern neural architectures, a recent work [45] proposed an information-theoretic objective function called Sparse Rate Reduction (SRR) and interpreted its unrolled optimization as a Transformer-like model called Coding Rate Reduction Transformer (CRATE). However, the focus of the study was primarily on the basic implementation, and whether this objective is optimized in practice and its causal relationship to generalization remain elusive. Going beyond this study, we derive different implementations by analyzing layer-wise behaviors of CRATE, both theoretically and empirically. To reveal the predictive power of SRR on generalization, we collect a set of model variants induced by varied implementations and hyperparameters and evaluate SRR as a complexity measure based on its correlation with generalization. Surprisingly, we find out that SRR has a positive correlation coefficient and outperforms other baseline measures, such as path-norm and sharpness-based ones. Furthermore, we show that generalization can be improved using SRR as regularization on benchmark image classification datasets. We hope this paper can shed light on leveraging SRR to design principled models and study their generalization ability. © 2024, CC BY.

关键词：

来源：评论

学校读者我要写书评

暂无评论

The implicit bias of adam on separable data 24

The implicit bias of adam on separable data

引用

Proceedings of the 38th International Conference on Neural Information Processing Systems

作者： Chenyang Zhang Difan Zou Yuan Cao Department of Statistics and Actuarial Science School of Computing and Data Science The University of Hong Kong Department of Computer Science School of Computing and Data Science & Institute of Data Science The University of Hong Kong Department of Statistics and Actuarial Science School of Computing and Data Science & Department of Mathematics The University of Hong Kong

ISBN: (纸本)9798331314385

Adam has become one of the most favored optimizers in deep learning problems. Despite its success in practice, numerous mysteries persist regarding its theoretical understanding. In this paper, we study the implicit bias of Adam in linear logistic regression. Specifically, we show that when the training data are linearly separable, the iterates of Adam converge towards a linear classifier that achieves the maximum ℓ∞ -margin in direction. Notably, for a general class of diminishing learning rates, this convergence occurs within polynomial time. Our result shed light on the difference between Adam and (stochastic) gradient descent from a theoretical perspective.

关键词：

来源：评论

学校读者我要写书评

暂无评论

TransFeat-TPP: An Interpretable Deep Covariate Temporal Point Processes 27

TransFeat-TPP: An Interpretable Deep Covariate Temporal Poin...

引用

27th European Conference on Artificial Intelligence, ECAI 2024

作者： Meng, Zizhuo Li, Boyu Fan, Xuhui Li, Zhidong Wang, Yang Chen, Fang Zhou, Feng Data Science Institute University of Technology Sydney Australia School of Computing Macquarie University Australia Center for Applied Statistics School of Statistics Renmin University of China China Beijing Advanced Innovation Center for Future Blockchain and Privacy Computing China

ISBN: (纸本)9781643685489

The classical temporal point process (TPP) constructs an intensity function by taking the occurrence times into account. Nevertheless, occurrence time may not be the only relevant factor, other contextual data, termed covariates, may also impact the event evolution. Incorporating such covariates into the model is beneficial, while distinguishing their relevance to the event dynamics is of great practical significance. In this work, we propose a Transformer-based covariate temporal point process (TransFeat-TPP) model to improve the interpretability of deep covariate-TPPs while maintaining powerful expressiveness. TransFeat-TPP can effectively model complex relationships between events and covariates, and provide enhanced interpretability by discerning the importance of various covariates. Experimental results on synthetic and real datasets demonstrate improved prediction accuracy and consistently interpretable feature importance when compared to existing deep covariate-TPPs. Our code is available at https://***/waystogetthere/***. © 2024 The Authors.

关键词： Spatio-temporal data

来源：评论

学校读者我要写书评

暂无评论

CurricularVPR: Curricular Contrastive Loss for Visual Place Recognition

CurricularVPR: Curricular Contrastive Loss for Visual Place ...

引用

2024 IEEE/RSJ International Conference on Intelligent Robots and Systems, IROS 2024

作者： Zhang, Dongshuo Chen, Nanhua Wu, Meiqing Lam, Siew-Kei Nanyang Technological University College of Computing and Data Science 50 Nanyang Ave 639798 Singapore Beijing Institute of Technology School of Aerospace Engineering Beijing100081 China

ISBN: (纸本)9798350377705

Visual Place Recognition (VPR) techniques commonly utilize Contrastive Losses (CL) to train models that generate compact and discriminative global descriptors for images. These models often result in poor performance due to one of the following reasons during training: 1) loss functions that focus primarily on easier samples, 2) reliance on time-consuming hard sample mining methods to identify informative supervisory samples, which hinders effective learning from large-scale datasets. To enhance both learning efficiency and effectiveness, we propose a Curricular Contrastive Loss (CCL) and use graded similarity labels as a measure of sample difficulty. Inspired by human learning that begin with easier concepts and progressively tackle more challenging ones, our CCL dynamically emphasizes easier samples during the initial training stages to achieve rapid convergence. The learning gradually focuses on harder samples in later training stages to bolster robustness of the models under challenging conditions. Our proposed method has been extensively evaluated on popular datasets, and the results demonstrate its superior performance compared to the CL and Generalized CL functions. © 2024 IEEE.

关键词： Contrastive Learning

来源：评论

学校读者我要写书评

暂无评论

Time Matters: An End-to-End Solution for Temporal Claim Verification

Time Matters: An End-to-End Solution for Temporal Claim Veri...

引用

2024 Conference on Empirical Methods in Natural Language Processing, EMNLP 2024

作者： Barik, Anab Maulana Hsu, Wynne Lee, Mong Li School of Computing National University of Singapore Singapore Institute of Data Science National University of Singapore Singapore Centre for Trusted Internet & Community National University of Singapore Singapore

ISBN: (纸本)9798891761667

Automated claim verification plays an essential role in fostering trust in the digital space. Temporal claim verification brings new challenges where cues of the temporal information need to be extracted, and temporal reasoning involving various temporal aspects of the text must be applied. In this work, we describe an end-to-end solution for temporal claim verification that considers the temporal information in claims to obtain relevant evidence sentences and harnesses the power of a large language model for temporal reasoning. We curate two datasets comprising a diverse range of temporal claims to learn time-sensitive representations that encapsulate not only the semantic relationships among the events, but also their chronological proximity. Experiment results demonstrate that the proposed approach significantly enhances the accuracy of temporal claim verification, thereby advancing current state-of-the-art in automated claim verification. © 2024 Association for Computational Linguistics.

关键词： Spatio-temporal data

来源：评论

学校读者我要写书评

暂无评论

MG-Net: Learn to Customize QAOA with Circuit Depth Awareness 38

MG-Net: Learn to Customize QAOA with Circuit Depth Awareness

引用

38th Conference on Neural Information Processing Systems, NeurIPS 2024

作者： Qian, Yang Wang, Xinbiao Du, Yuxuan Luo, Yong Tao, Dacheng School of Computer Science Faculty of Engineering University of Sydney NSW2008 Australia Institute of Artificial Intelligence School of Computer Science Wuhan University Wuhan China College of Computing and Data Science Nanyang Technological University Singapore639798 Singapore

Quantum Approximate Optimization Algorithm (QAOA) and its variants exhibit immense potential in tackling combinatorial optimization challenges. However, their practical realization confronts a dilemma: the requisite circuit depth for satisfactory performance is problem-specific and often exceeds the maximum capability of current quantum devices. To address this dilemma, here we first analyze the convergence behavior of QAOA, uncovering the origins of this dilemma and elucidating the intricate relationship between the employed mixer Hamiltonian, the specific problem at hand, and the permissible maximum circuit depth. Harnessing this understanding, we introduce the Mixer Generator Network (MG-Net), a unified deep learning framework adept at dynamically formulating optimal mixer Hamiltonians tailored to distinct tasks and circuit depths. Systematic simulations, encompassing Ising models and weighted Max-Cut instances with up to 64 qubits, substantiate our theoretical findings, highlighting MG-Net's superior performance in terms of both approximation ratio and efficiency. © 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

Improving VTE Identification through Adaptive NLP Model Selection and Clinical Expert Rule-based Classifier from Radiology Reports

Improving VTE Identification through Adaptive NLP Model Sele...

引用

2023 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2023

作者： Deng, Jamie Wu, Yusen Hayssen, Hilary Englum, Brain Kankaria, Aman Mayorga-Carlin, Minerva Sahoo, Shalini Sorkin, John Lal, Brajesh Yesha, Yelena Nguyen, Phuong University of Miami Frost Institute for Data Science & Computing FL United States University of Maryland School of Medicine MD United States

ISBN: (纸本)9798350337488

Rapid and accurate identification of Venous thromboembolism (VTE), a severe cardiovascular condition including deep vein thrombosis (DVT) and pulmonary embolism (PE), is important for effective treatment. Leveraging Natural Language Processing (NLP) on radiology reports, automated methods have shown promising advancements in identifying VTE events from retrospective data cohorts or aiding clinical experts in identifying VTE events from radiology reports. However, effectively training Deep Learning (DL) and the NLP models is challenging due to limited labeled medical text data, the complexity and heterogeneity of radiology reports, and data imbalance. This study proposes novel method combinations of DL methods, along with data augmentation, adaptive pre-trained NLP model selection, and a clinical expert NLP rule-based classifier, to improve the accuracy of VTE identification in unstructured (free-text) radiology reports. Our experimental results demonstrate the model's efficacy, achieving an impressive 97% accuracy and 97% F1 score in predicting DVT, and an outstanding 98.3% accuracy and 98.4% F1 score in predicting PE. These findings emphasize the model's robustness and its potential to significantly contribute to VTE research. © 2023 IEEE.

关键词： BERT Bi-LSTM Deep Learning NLP Transfer Learning VTE

来源：评论

学校读者我要写书评

暂无评论

BERD+: A Generic Sequential Recommendation Framework by Eliminating Unreliable data with Item- and Attribute-level Signals

引用

ACM Transactions on Information Systems 2023年第2期42卷 1-33页

作者： Sun, Yatong Yang, Xiaochun Sun, Zhu Wang, Bin School of Computer Science and Engineering Northeastern University School of Computing Macquarie University China Australia Institute of High Performance Computing Centre for Frontier AI Research A*STAR Singapore School of Computer Science and Engineering Northeastern University China National Frontiers Science Center for Industrial Intelligence and Systems Optimization China Key Laboratory of Data Analytics and Optimization for Smart Industry [Northeastern University Ministry of Education China

A preliminary work of our study was published at IJCAI’21 [47], which is substantially extended in the following aspects: (1) In Section 1, we analyze the necessity of introducing item attributes for detecting unreliable instances, together with the problems and challenges that attributes may bring in. (2) In Section 2, we add discussions about the limitations of existing attribute-aware recommender systems (Section 2.2) and denoising methods (Section 2.3) in the context of detecting unreliable instances. (3) In Section 4.2, we further conduct an in-depth analysis at the attribute level to demonstrate the capability of attributes for rectifying instance loss and uncertainty, as well as the disturbance caused by attributes. (4) We generalize BERD to a generic framework BERD+ in Section 5.1, equipped with novel modules, i.e., HU-GCN (Section 5.2) and EPE (Section 5.4), which properly incorporate item attributes while reducing their disturbance for rectifying instance uncer tainty (Section 5.5) and loss (Section 5.6). The generic BERD+ can be flexibly plugged into existing SRSs for performance enhanced recommendation via eliminating unreliable data. (5) In Section 6.2, we apply our BERD+ framework to seven state-of-the-art SRSs on five real-world datasets to illustrate its superiority. (6) To avoid unfair comparison caused by item attributes, we build and compare with the baseline that combines the original BERD and an advanced attribute-aware recommender system, KSR [19]. (7) For more comprehensive comparison, in Section 6.2.2, we compare BRED+ with two state-of-the-art denoising approaches;in Section 6.2.3, to examine the efficacy of HU-GCN and EPE, we compare HU-GCN with various attribute embedding techniques, i.e., variants of graph neural networks, and compare EPE with different attribute fusing methods, i.e., adding, concatenation, and weighted sum. (8) In Section 6.2.4, a detailed ablation study is conducted to verify the effectiveness of each module of BERD+. (

关键词： Convolution

来源：评论

学校读者我要写书评

暂无评论

MusCare+: Muscle Monitoring for Anomalies

MusCare+: Muscle Monitoring for Anomalies

引用

2022 IEEE World AI IoT Congress, AIIoT 2022

作者： Foley, Nicholas Yu, Chen-Hsiang School of Computing and Data Science Wentworth Institute of Technology BostonMA United States

ISBN: (纸本)9781665484534

Muscles are an essential part of everyday life and any damage or illness that affects them can cause massive problems. Patients who are diagnosed with muscle injuries and illnesses largely remain unmonitored, even though a few appointments they have with doctors annually. Moving from unmonitored to constant monitoring can not only paint a better picture of how a muscle condition is progressing, but it also can inform medical professionals if their treatment regimen is actually working. In this paper, we propose a new system that can monitor muscle health of a patient and predict the muscle conditions. This system mainly focuses on the shoulder but could be expanded to other areas of the body. By utilizing the strength of machine learning and the Android platform, we created a platform that can monitor muscle health quickly and easily. The current prototype system is not only able to display live data gathered from an EMG sensor, but it can also predict whether the muscle is currently flexed or relaxed. Although there is a limitation in current prototype system, a more robust machine learning algorithm could be trained to give a wide array of muscle health predictions. copy;2022 IEEE. © 2022 IEEE.

关键词： Forecasting

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：