检索结果-内蒙古大学图书馆

BLESSEMFLOOD21: ADVANCING FLOOD ANALYSIS WITH A HIGH-RESOLUTION GEOREFERENCED dataSET FOR HUMANITARIAN AID SUPPORT

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Polushko, Vladyslav Jenal, Alexander Bongartz, Jens Weber, Immanuel Hatic, Damjan Rösch, Ronald März, Thomas Rauhut, Markus Weinmann, Andreas Image Processing Department Fraunhofer ITWM Kaiserslautern Germany Working Group Algorithms for Computer Vision Imaging and Data Analysis Hochschule Darmstadt Darmstadt Germany Center for Machine Learning and Sensor Technology Hochschule Koblenz Remagen Germany

Floods are an increasingly common global threat, causing emergencies and severe damage to infrastructure. During crises, organisations such as the World Food Programme use remotely sensed imagery, typically obtained through drones, for rapid situational analysis to plan life-saving actions. Computer Vision tools are needed to support task force experts on-site in the evaluation of the imagery to improve their efficiency and to allocate resources strategically. We introduce the BlessemFlood21 dataset to stimulate research on efficient flood detection tools. The imagery was acquired during the 2021 Erftstadt-Blessem flooding event and consists of high-resolution and georeferenced RGB-NIR images. In the resulting RGB dataset, the images are supplemented with detailed water masks, obtained via a semi-supervised human-in-the-loop technique, where in particular the NIR information is leveraged to classify pixels as either water or non-water. We evaluate our dataset by training and testing established Deep learning models for semantic segmentation. With BlessemFlood21 we provide labeled high-resolution RGB data and a baseline for further development of algorithmic solutions tailored to flood detection in RGB imagery. © 2024, CC BY-NC-ND.

关键词： Floods

Sampling Strategies for Compressive Imaging Under Statistical Noise

学校读者我要写书评

暂无评论

Sampling Strategies for Compressive Imaging Under Statistica...

2023 International Conference on Sampling Theory and Applications, SampTA 2023

作者： Hoppe, Frederik Krahmer, Felix Verdun, Claudio Mayrink Menzel, Marion I. 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 Technical University of Munich Munich Data Science Institute Germany Technische Hochschule Ingolstadt AImotion Bavaria Ingolstadt Germany Technical University of Munich Department of Physics Garching Germany Ge Healthcare Munich Germany

ISBN: (纸本)9798350328851

Most of the compressive sensing literature in signal processing assumes that the noise present in the measurement has an adversarial nature, i.e., it is bounded in a certain norm. At the same time, the randomization introduced in the sampling scheme usually assumes an i.i.d. model where rows are sampled with replacement. In this case, if a sample is measured a second time, it does not add additional information. For many applications, where the statistical noise model is a more accurate one, this is not true anymore since a second noisy sample comes with an independent realization of the noise, so there is a fundamental difference between sampling with and without replacement. Therefore, a more careful analysis must be performed. In this short note, we illustrate how one can mathematically transition between these two noise models. This transition gives rise to a weighted LASSO reconstruction method for sampling without replacement, which numerically improves the solution of high-dimensional compressive imaging problems. © 2023 IEEE.

关键词： Compressed sensing

Model and feature diversity for bayesian neural networks in mutual learning 23

学校读者我要写书评

暂无评论

Model and feature diversity for bayesian neural networks in ...

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

作者： Cuong Pham Cuong C. Nguyen Trung Le Dinh Phung Gustavo Carneiro Thanh-Toan Do Department of Data Science and AI Monash University Australia Australian Institute for Machine Learning University of Adelaide Australia Department of Data Science and AI Monash University Australia and VinAI Vietnam Centre for Vision Speech and Signal Processing University of Surrey United Kingdom

Bayesian Neural Networks (BNNs) offer probability distributions for model parameters, enabling uncertainty quantification in predictions. However, they often underperform compared to deterministic neural networks. Utilizing mutual learning can effectively enhance the performance of peer BNNs. In this paper, we propose a novel approach to improve BNNs performance through deep mutual learning. The proposed approaches aim to increase diversity in both network parameter distributions and feature distributions, promoting peer networks to acquire distinct features that capture different characteristics of the input, which enhances the effectiveness of mutual learning. Experimental results demonstrate significant improvements in the classification accuracy, negative log-likelihood, and expected calibration error when compared to traditional mutual learning for BNNs.

关键词：

Position: insights from survey methodology can improve training data 24

学校读者我要写书评

暂无评论

Position: insights from survey methodology can improve train...

Proceedings of the 41st International Conference on machine learning

作者： Stephanie Eckman Barbara Plank Frauke Kreuter Social Data Science Center University of Maryland College Park MD Center for Information and Language Processing (CIS) LMU Munich Germany and Computer Science Department IT University of Copenhagen Denmark and Munich Center for Machine Learning (MCML) LMU Munich Germany Institute for Statistics and Munich Center for Machine Learning (MCML) LMU Munich Germany and Social Data Science Center and Joint Program in Survey Methodology University of Maryland College Park MD

Whether future AI models are fair, trustworthy, and aligned with the public's interests rests in part on our ability to collect accurate data about what we want the models to do. However, collecting high-quality data is difficult, and few AI/ML researchers are trained in data collection methods. Recent research in data-centric AI has show that higher quality training data leads to better performing models, making this the right moment to introduce AI/ML researchers to the field of survey methodology, the science of data collection. We summarize insights from the survey methodology literature and discuss how they can improve the quality of training and feedback data. We also suggest collaborative research ideas into how biases in data collection can be mitigated, making models more accurate and human-centric.

关键词：

UNCERTAINTY QUANTIFICATION FOR LEARNED ISTA

学校读者我要写书评

暂无评论

arXiv 2023年

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

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. Copyright © 2023, The Authors. All rights reserved.

关键词： Deep learning

Uncertainty Quantification For Learned ISTA

学校读者我要写书评

暂无评论

Uncertainty Quantification For Learned ISTA

IEEE Workshop on machine learning for Signal processing

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

关键词：

BGTplanner: Maximizing Training Accuracy for Differentially Private Federated Recommenders via Strategic Privacy Budget Allocation

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Zhang, Xianzhi Zhou, Yipeng Hu, Miao Wu, Di Liao, Pengshan Guizani, Mohsen Sheng, Michael The School of Computer Science and Engineering Sun Yat-sen University Guangzhou China Guangdong Key Laboratory of Big Data Analysis and Processing Guangzhou China The Department of Computing Faculty of Science and Engineering Macquarie University Sydney Australia The Machine Learning Department Mohamed Bin Zayed University of Artificial Intelligence Abu Dhabi United Arab Emirates

To mitigate the rising concern about privacy leakage, the federated recommender (FR) paradigm emerges, in which decentralized clients co-train the recommendation model without exposing their raw user-item rating data. The differentially private federated recommender (DPFR) further enhances FR by injecting differentially private (DP) noises into clients. Yet, current DPFRs, suffering from noise distortion, cannot achieve satisfactory accuracy. Various efforts have been dedicated to improving DPFRs by adaptively allocating the privacy budget over the learning process. However, due to the intricate relation between privacy budget allocation and model accuracy, existing works are still far from maximizing DPFR accuracy. To address this challenge, we develop BGTplanner (Budget Planner) to strategically allocate the privacy budget for each round of DPFR training, improving overall training performance. Specifically, we leverage the Gaussian process regression and historical information to predict the change in recommendation accuracy with a certain allocated privacy budget. Additionally, Contextual Multi-Armed Bandit (CMAB) is harnessed to make privacy budget allocation decisions by reconciling the current improvement and long-term privacy constraints. Our extensive experimental results on real datasets demonstrate that BGTplanner achieves an average improvement of 6.76% in training performance compared to state-of-the-art baselines. Copyright © 2024, The Authors. All rights reserved.

关键词： Differential privacy

Contrastive Continual learning with Importance Sampling and Prototype-Instance Relation Distillation

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Li, Jiyong Azizov, Dilshod Li, Yang Liang, Shangsong School of Computer Science and Engineering Sun Yat-sen University China Guangdong Key Laboratory of Big Data Analysis and Processing Guangzhou China Department of Machine Learning Mohamed bin Zayed University of Artificial Intelligence United Arab Emirates AI Thrust Information Hub The Hong Kong University of Science and Technology Guangzhou China Department of CSE The Hong Kong University of Science and Technology China

Recently, because of the high-quality representations of contrastive learning methods, rehearsal-based contrastive continual learning has been proposed to explore how to continually learn transferable representation embeddings to avoid the catastrophic forgetting issue in traditional continual settings. Based on this framework, we propose Contrastive Continual learning via Importance Sampling (CCLIS) to preserve knowledge by recovering previous data distributions with a new strategy for Replay Buffer Selection (RBS), which minimize estimated variance to save hard negative samples for representation learning with high quality. Furthermore, we present the Prototype-instance Relation Distillation (PRD) loss, a technique designed to maintain the relationship between prototypes and sample representations using a self-distillation process. Experiments on standard continual learning benchmarks reveal that our method notably outperforms existing baselines in terms of knowledge preservation and thereby effectively counteracts catastrophic forgetting in online contexts. The code is available at https://***/lijy373/CCLIS. Copyright © 2024, The Authors. All rights reserved.

关键词： Distillation

Sampling Strategies for Compressive Imaging Under Statistical Noise

学校读者我要写书评

暂无评论

Sampling Strategies for Compressive Imaging Under Statistica...

International Conference on Sampling Theory and Applications (SampTA)

作者： Frederik Hoppe Felix Krahmer Claudio Mayrink Verdun Marion I. Menzel Holger Rauhut Chair of Mathematics of Information Processing RWTH Aachen University Aachen Germany Department of Mathematics Technical University of Munich Munich Germany Munich Center for Machine Learning Munich Germany Munich Data Science Institute Technical University of Munich AImotion Bavaria Technische Hochschule Ingolstadt Ingolstadt Germany Department of Physics Technical University of Munich Garching Germany GE Healthcare Munich Germany

关键词：