检索结果-内蒙古大学图书馆

Conference on Computer Vision and Pattern Recognition (CVPR)

作者： Islam Nassar Munawar Hayat Ehsan Abbasnejad Hamid Rezatofighi Gholamreza Haffari Data Science and AI Department Monash University Australia Australian Institute for Machine Learning The University of Adelaide Australia

Confidence-based pseudo-labeling is among the dominant approaches in semi-supervised learning (SSL). It relies on including high-confidence predictions made on unlabeled data as additional targets to train the model. We propose Protocon, a novel SSL method aimed at the less-explored label-scarce SSL where such methods usually underperform. Protocon refines the pseudolabels by lever-aging their nearest neighbours' information. The neighbours are identified as the training proceeds using an online clustering approach operating in an embedding space trained via a prototypical loss to encourage well-formed clusters. The online nature of Protocon allows it to utilise the label history of the entire dataset in one training cycle to refine labels in the following cycle without the need to store image embeddings. Hence, it can seamlessly scale to larger datasets at a low cost. Finally, Protocon addresses the poor training signal in the initial phase of training (due to fewer confident predictions) by introducing an auxiliary self-supervised loss. It delivers significant gains and faster convergence over state-of-the-art across 5 datasets, including CIFARs, ImageNet and DomainNet.

关键词：

来源：评论

学校读者我要写书评

暂无评论

PROTOCON: Pseudo-label Refinement via Online Clustering and Prototypical Consistency for Efficient Semi-supervised learning

arXiv

引用

arXiv 2023年

作者： Nassar, Islam Hayat, Munawar Abbasnejad, Ehsan Rezatofighi, Hamid Haffari, Gholamreza Data Science and AI Department Monash University Australia Australian Institute for Machine Learning The University of Adelaide Australia

Confidence-based pseudo-labeling is among the dominant approaches in semi-supervised learning (SSL). It relies on including high-confidence predictions made on unlabeled data as additional targets to train the model. We propose PROTOCON, a novel SSL method aimed at the less-explored label-scarce SSL where such methods usually underperform. PROTOCON refines the pseudo-labels by leveraging their nearest neighbours' information. The neighbours are identified as the training proceeds using an online clustering approach operating in an embedding space trained via a prototypical loss to encourage well-formed clusters. The online nature of PROTOCON allows it to utilise the label history of the entire dataset in one training cycle to refine labels in the following cycle without the need to store image embeddings. Hence, it can seamlessly scale to larger datasets at a low cost. Finally, PROTOCON addresses the poor training signal in the initial phase of training (due to fewer confident predictions) by introducing an auxiliary self-supervised loss. It delivers significant gains and faster convergence over state-of-the-art across 5 datasets, including CIFARs, ImageNet and DomainNet. © 2023, CC BY-SA.

关键词： Embeddings

来源：评论

学校读者我要写书评

暂无评论

EXACT CERTIFICATION OF (GRAPH) NEURAL NETWORKS AGAINST LABEL POISONING

arXiv

引用

arXiv 2024年

作者： Sabanayagam, Mahalakshmi Gosch, Lukas Günnemann, Stephan Ghoshdastidar, Debarghya School of Computation Information and Technology Germany Munich Data Science Institute Technical University of Munich Germany Munich Center for Machine Learning Germany

machine learning models are highly vulnerable to label flipping, i.e., the adversarial modification (poisoning) of training labels to compromise performance. Thus, deriving robustness certificates is important to guarantee that test predictions remain unaffected and to understand worst-case robustness behavior. However, for Graph Neural Networks (GNNs), the problem of certifying label flipping has so far been unsolved. We change this by introducing an exact certification method, deriving both sample-wise and collective certificates. Our method leverages the Neural Tangent Kernel (NTK) to capture the training dynamics of wide networks enabling us to reformulate the bilevel optimization problem representing label flipping into a Mixed-Integer Linear Program (MILP). We apply our method to certify a broad range of GNN architectures in node classification tasks. Thereby, concerning the worst-case robustness to label flipping: (i) we establish hierarchies of GNNs on different benchmark graphs;(ii) quantify the effect of architectural choices such as activations, depth and skip-connections;and surprisingly, (iii) uncover a novel phenomenon of the robustness plateauing for intermediate perturbation budgets across all investigated datasets and architectures. While we focus on GNNs, our certificates are applicable to sufficiently wide NNs in general through their NTK. Thus, our work presents the first exact certificate to a poisoning attack ever derived for neural networks, which could be of independent interest. The code is available at https://***/saper0/qpcert. © 2024, CC BY.

关键词： Budget control

来源：评论

学校读者我要写书评

暂无评论

Vehicle Prediction for BUS Identification Output from our Route Testing Real Time Algorithm 5

Vehicle Prediction for BUS Identification Output from our Ro...

引用

5th International Conference on Sustainable Communication Networks and Application, ICSCNA 2024

作者： Misba, M. Ramya, R. Dickson, Joel Sharmila, L. Kavitha, J. Udayakumar, K. Vel Tech Rangarajan Dr. Sagunthala R&D Institute of Science and Technology Department of Artificial Intelligence and Machine Learning Tamil Nadu India St. Joseph's College of Engineering Department of Artificial Intelligence and Data Science Chennai India Bethlehem Institute of Engineering Tamil Nadu Karungal India Vel Tech Rangarajan Dr. Sagunthala R&D Institute of Science and Technology Department of Computer Science and Engineering Tamil Nadu India

ISBN: (纸本)9798331530013

Traffic generation in Indian cities is of a mixed nature, comprising over a dozen types of vehicles that can be broadly categorized into slow-moving and fast-moving vehicles. This study highlights the challenges associated with the inefficient operation of the existing bus system. GPS and mobile networks form integral components of the current system, enabling data storage and management using PostgreSQL. The system provides robust and reliable data to fulfill requests from other software applications. Operating on cloud platforms, it is compatible with all major web browsers. The proposed algorithm continuously tracks the real-time location of buses and their corresponding WMS (Web Map Service) location, alerting users through marker notifications. This paper also explores measures to evaluate the efficiency and effectiveness of bus services. Recognizing that an inadequate public transport system impedes economic growth and development, this study emphasizes the need to enhance the overall quality and accessibility of public transportation. The findings aim to improve the operational efficiency of bus services, contributing to a more effective and sustainable transport system. © 2024 IEEE.

关键词： Buses

来源：评论

学校读者我要写书评

暂无评论

The Role of IoT and machine learning in Automating Space Docking: Challenges, Advancements, and Future Prospects 2

The Role of IoT and Machine Learning in Automating Space Doc...

引用

2nd International Conference on machine learning and Autonomous Systems, ICMLAS 2025

作者： Jikar, Nayan Tale, Yash Tale, Abhay Barhate, Aditya Verma, Prateek Jikar, Aman Datta Meghe Institute of Higher Education and Research Faculty of Engineering and Technology Department of Artificial Intelligence and Machine Learning Maharashtra Wardha442001 India Datta Meghe Institute of Higher Education and Research Faculty of Engineering and Technology Department of Artificial Intelligence and Data Science Maharashtra Wardha442001 India Datta Meghe Institute of Higher Education and Research Faculty of Engineering and Technology Department of Computer Science and Engineering Maharashtra Wardha442001 India

ISBN: (纸本)9798331505745

Space docking is an important aspect of modern-day space exploration, enabling crewed missions, shipment transport, and spacecraft refuelling. Traditionally, manual docking has trusted astronaut precision and floor manipulation coordination, which has grown to be inefficient and blunders-susceptible in deep-space missions because of conversation delays. Integrating the Internet of Things (IoT) and machine learning (ML) is reworking area docking by introducing self-reliant, actual-time selection-making structures. IoT-enabled sensors continuously monitor spacecraft role, pace, and orientation, while ML algorithms optimize docking manoeuvres, beautify predictive upkeep, and make certain collision avoidance. Reinforcement learning similarly allows adaptive management strategies, making self-sufficient docking more efficient and dependable. This paper explores the improvements in IoT and ML for automating space docking, reading real-global programs along with SpaceX Dragon, NASA's AR&D systems, and China's Tianzhou cargo deliver. By addressing key demanding situations-precision, pace, and safety-those technologies pave the way for sustainable space exploration, including future Mars missions and autonomous area stations. The observation highlights how AI-driven docking may be integral for deep-space operations, making sure safer and more green missions are made. © 2025 IEEE.

关键词： Reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

Role of machine learning in Climate Change Prediction and Mitigation 2

Role of Machine Learning in Climate Change Prediction and Mi...

引用

2nd International Conference on machine learning and Autonomous Systems, ICMLAS 2025

ISBN: (纸本)9798331505745

Climate change is one of the biggest challenges of the 21st century, with profound environmental, economic, and social impacts. machine learning (ML) has emerged as a transformative tool to address climate challenges through data-driven solutions, offering predictive capabilities for extreme weather events and enhancing the efficiency of clean-energy systems. This technology benefits the optimization of renewable energy generation, intelligent grid management, and resource utilization towards reducing greenhouse gas emissions. Moreover, ML promotes climate justice through targeted region-specific intervention and inclusive solution-making for the most vulnerable. Several technical and ethical challenges associated with data quality, scalability, and model generalization must still be overcome for ML to realize its potential. This paper reviews the role of ML in climate change prediction and mitigation discusses ongoing real-world applications and outlines the future research agenda necessary to address existing challenges. Integrating ML with emerging technologies like the Internet of Things (IoT) and explainable AI, alongside global collaboration and a focus on climate justice, will be essential in advancing effective climate action. © 2025 IEEE.

关键词： Global warming

来源：评论

学校读者我要写书评

暂无评论

Uncertainty Quantification For Learned ISTA 33

Uncertainty Quantification For Learned ISTA

引用

33rd IEEE International Workshop on machine learning for Signal Processing, MLSP 2023

作者： Hoppe, Frederik Verdun, Claudio Mayrink Laus, Hannah Krahmer, Felix Rauhut, Holger Rwth Aachen University Chair of Mathematics of Information Processing Aachen Germany Technical University of Munich Department of Mathematics Munich Germany Munich Center for Machine Learning Munich Germany Munich Data Science Institute Technical University of Munich Munich Germany

ISBN: (纸本)9798350324112

Model-based deep learning solutions to inverse problems have attracted increasing attention in recent years as they bridge state-of-the-art numerical performance with interpretability. In addition, the incorporated prior domain knowledge can make the training more efficient as the smaller number of parameters allows the training step to be executed with smaller datasets. Algorithm unrolling schemes stand out among these model-based learning techniques. Despite their rapid advancement and their close connection to traditional high-dimensional statistical methods, they lack certainty estimates and a theory for uncertainty quantification is still elusive. This work provides a step towards closing this gap proposing a rigorous way to obtain confidence intervals for the LISTA estimator. © 2023 IEEE.

关键词： Deep learning

来源：评论

学校读者我要写书评

暂无评论

Facial Expression Recognition Using Multi-Block Deep CNN 5

Facial Expression Recognition Using Multi-Block Deep CNN

引用

5th International Conference on Circuits, Control, Communication and Computing, I4C 2024

作者： Priyadarshini, V. Srinivasulu Reddy, U. Reddy Chirra, Venkata Rami Mrudula, M. Suneetha, M. National Institute of Technology Dept. of Computer Science & Engineering Andhra Pradesh India Machine Learning & Data Analytics Lab National Institute of Technology Dept. of Computer Applications Tiruchirappalli India School of Computer Science & Engineering VIT-AP University Amaravathi India Malla Reddy College of Engineering Department of CSE Telangana India Independent Researcher Amaravati India

ISBN: (纸本)9798331528539

Emotions play a crucial role in decision-making, moral judgments, and other cognitive processes. The goal of this work is to identify people's facial emotions from face images. Facial expression recognition (FER), a highly diverse field with many commonalities between classes, is a challenging problem. The capabilities of current FER systems are limited in this regard. In this work, a multi-block Deep Convolutional Neural Networks (DCNN) model was proposed to identify facial expressions. Five blocks with different computational components were defined in a multi-block DCNN to extract the unique characteristics from input images. The second model (DCNN-SVM) is developed with an ensemble of SVM classifier to improve predictability and stability. The third model (DCNN-MV) is based on the majority voting with 4 classifiers SVM, KNN, Random Forest, and Decision Tree. The CK+ dataset was utilized and expanded via image data augmentation to enhance model performance and generalization. By adjusting hyperparameters, the suggested DCNN model's accuracy was investigated. The DCNN model reports an accuracy score of 97.71%. Both DCNN-SVM and DCNN-MV models achieved 97.79% accuracy. On the CK+ dataset, the proposed models demonstrated good accuracy in identifying facial expressions. When compared to existing models, the proposed model outperformed existing models in terms of accuracy. © 2024 IEEE.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Counterfactually comparing abstaining classifiers 23

Counterfactually comparing abstaining classifiers

引用

Proceedings of the 37th International Conference on Neural Information Processing Systems

作者： Yo Joong Choe Aditya Gangrade Aaditya Ramdas Data Science Institute University of Chicago Department of EECS University of Michigan Dept. of Statistics and Data Science Machine Learning Department Carnegie Mellon University

Abstaining classifiers have the option to abstain from making predictions on inputs that they are unsure about. These classifiers are becoming increasingly popular in high-stakes decision-making problems, as they can withhold uncertain predictions to improve their reliability and safety. When evaluating black-box abstaining classifier(s), however, we lack a principled approach that accounts for what the classifier would have predicted on its abstentions. These missing predictions matter when they can eventually be utilized, either directly or as a backup option in a failure mode. In this paper, we introduce a novel approach and perspective to the problem of evaluating and comparing abstaining classifiers by treating abstentions as missing data. Our evaluation approach is centered around defining the counterfactual score of an abstaining classifier, defined as the expected performance of the classifier had it not been allowed to abstain. We specify the conditions under which the counterfactual score is identifiable: if the abstentions are stochastic, and if the evaluation data is independent of the training data (ensuring that the predictions are missing at random), then the score is identifiable. Note that, if abstentions are deterministic, then the score is unidentifiable because the classifier can perform arbitrarily poorly on its abstentions. Leveraging tools from observational causal inference, we then develop nonparametric and doubly robust methods to efficiently estimate this quantity under identification. Our approach is examined in both simulated and real data experiments.

关键词：

来源：评论

学校读者我要写书评

暂无评论

A Review on the Developments in the Field of AI-Based Gait Analysis 2

A Review on the Developments in the Field of AI-Based Gait A...

引用

2nd DMIHER International Conference on Artificial Intelligence in Healthcare, Education and Industry, IDICAIEI 2024

作者： Wankhede, Vidhi Verma, Prateek Gahane, Shailesh Faculty of Engineering and Technology Department of Artificial Intelligence and Data Science Maharashtra Wardha442001 India Faculty of Engineering and Technology Department of Artificial Intelligence and Machine Learning Maharashtra Wardha442001 India Datta Meghe Institute of Higher Education and Research Faculty of Sciences and Technology Maharashtra Wardha442001 India

ISBN: (纸本)9798331528713

The examination of human gait is essential for comprehending motor function, the evolution of diseases, and the effectiveness of rehabilitation in different clinical and research environments. Artificial Intelligence (AI) advancements have recently improved gait analysis methodologies, resulting in increased accuracy, efficiency, and therapeutic effectiveness. This review article compiles the existing literature on AI-based gait analysis. The review emphasizes the role of AI in gait analysis, namely via the use of vision-based approaches, wearable sensor technologies, markerless motion capture systems, and inertial sensor-based methodologies. AI has shown potential in identifying musculoskeletal problems including osteopenia and sarcopenia, forecasting the start of Parkinson's disease, assessing the effects of post-stroke rehabilitation, and diagnosing neurological conditions. In addition, the integration of AI with new technologies such as augmented reality (AR), smart sensors, and wearable devices presents intriguing opportunities to improve gait rehabilitation, enable individualized therapies, and facilitate remote patient monitoring. Although there have been significant breakthroughs, there are still obstacles in creating AI models that can be easily understood for clinical decision-making, establishing standardized procedures for collecting data, and verifying AI algorithms across various populations. This study underlines the transformational potential of AI-based gait analysis in customized healthcare, rehabilitation techniques, and clinical results. In order to fully harness the potential of AI in enhancing human health and well-being, it is imperative to do more research and foster multidisciplinary cooperation. © 2024 IEEE.

关键词： Clinical research

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：