English
Related papers

Related papers: Reliable deep-learning-based phase imaging with un…

200 papers

The inability of artificial neural networks to assess the uncertainty of their predictions is an impediment to their widespread use. We distinguish two types of learnable uncertainty: model uncertainty due to a lack of training data and…

Machine Learning · Computer Science 2022-06-14 Hans Weytjens , Jochen De Weerdt

Label Distribution Learning (LDL) aims to characterize the polysemy of an instance by building a set of descriptive degrees corresponding to the instance. In recent years, researchers seek to model to obtain an accurate label distribution…

Machine Learning · Computer Science 2025-04-03 Pu Wang , Yu Zhang , Zhuoran Zheng

Accurate and reliable tumor segmentation is essential in medical imaging analysis for improving diagnosis, treatment planning, and monitoring. However, existing segmentation models often lack robust mechanisms for quantifying the…

Image and Video Processing · Electrical Eng. & Systems 2025-03-14 Seyed Sina Ziaee , Farhad Maleki , Katie Ovens

Reliability is of paramount importance for the physical layer of wireless systems due to its decisive impact on end-to-end performance. However, the uncertainty of prevailing deep learning (DL)-based physical layer algorithms is hard to…

Signal Processing · Electrical Eng. & Systems 2023-02-07 Wentao Yu , Hengtao He , Xianghao Yu , Shenghui Song , Jun Zhang , Khaled B. Letaief

We propose a novel camera-based DNN method for 3D lane detection with uncertainty estimation. Our method is based on a semi-local, BEV, tile representation that breaks down lanes into simple lane segments. It combines learning a parametric…

Computer Vision and Pattern Recognition · Computer Science 2020-03-12 Netalee Efrat , Max Bluvstein , Noa Garnett , Dan Levi , Shaul Oron , Bat El Shlomo

Ubiquitous applications of Deep neural networks (DNNs) in different artificial intelligence systems have led to their adoption in solving challenging visualization problems in recent years. While sophisticated DNNs offer an impressive…

Computer Vision and Pattern Recognition · Computer Science 2024-06-28 Soumya Dutta , Faheem Nizar , Ahmad Amaan , Ayan Acharya

We propose a novel deep learning tool in order to study the evolution of dark energy models. The aim is to combine two architectures: the Recurrent Neural Networks (RNN) and the Bayesian Neural Networks (BNN), we named this full network as…

Cosmology and Nongalactic Astrophysics · Physics 2020-03-18 Celia Escamilla-Rivera , Maryi Alejandra Carvajal Quintero , S. Capozziello

Convolutional neural networks (CNNs) show impressive performance for image classification and detection, extending heavily to the medical image domain. Nevertheless, medical experts are sceptical in these predictions as the nonlinear…

Computer Vision and Pattern Recognition · Computer Science 2017-06-30 Waleed M. Gondal , Jan M. Köhler , René Grzeszick , Gernot A. Fink , Michael Hirsch

Recent deep learning approaches focus on improving quantitative scores of dedicated benchmarks, and therefore only reduce the observation-related (aleatoric) uncertainty. However, the model-immanent (epistemic) uncertainty is less…

Image and Video Processing · Electrical Eng. & Systems 2021-10-25 Dominik Narnhofer , Alexander Effland , Erich Kobler , Kerstin Hammernik , Florian Knoll , Thomas Pock

Deep Learning (DL) has achieved great success in many real applications. Despite its success, there are some main problems when deploying advanced DL models in database systems, such as hyper-parameters tuning, the risk of overfitting, and…

Databases · Computer Science 2021-07-20 Kangfei Zhao , Jeffrey Xu Yu , Zongyan He , Hao Zhang

Deep neural networks (DNNs) achieve promising performance in visual recognition under the independent and identically distributed (IID) hypothesis. In contrast, the IID hypothesis is not universally guaranteed in numerous real-world…

Image and Video Processing · Electrical Eng. & Systems 2023-06-27 Shuai Wang , Zipei Yan , Daoan Zhang , Zhongsen Li , Sirui Wu , Wenxuan Chen , Rui Li

We introduce a physics-informed Bayesian Neural Network (BNN) with flow approximated posteriors using multiplicative normalizing flows (MNF) for detailed uncertainty quantification (UQ) at the physics event-level. Our method is capable of…

Machine Learning · Computer Science 2023-10-05 Cristiano Fanelli , James Giroux

Deep learning models are now used in many different industries, while in certain domains safety is not a critical issue in the medical field it is a huge concern. Not only, we want the models to generalize well but we also want to know the…

Machine Learning · Computer Science 2019-07-08 Jae Duk Seo

Uncertainty quantification is an important and challenging problem in deep learning. Previous methods rely on dropout layers which are not present in modern deep architectures or batch normalization which is sensitive to batch sizes. In…

Computer Vision and Pattern Recognition · Computer Science 2020-07-10 Lukasz Wandzik , Raul Vicente Garcia , Jörg Krüger

Brain vessel segmentation of MR scans is a critical step in the diagnosis of cerebrovascular diseases. Due to the fine vessel structure, manual vessel segmentation is time consuming. Therefore, automatic deep learning (DL) based…

Image and Video Processing · Electrical Eng. & Systems 2025-03-31 Omini Rathore , Richard Paul , Abigail Morrison , Hanno Scharr , Elisabeth Pfaehler

The ability of deep learning to predict with uncertainty is recognized as key for its adoption in clinical routines. Moreover, performance gain has been enabled by modelling uncertainty according to empirical evidence. While previous work…

Computer Vision and Pattern Recognition · Computer Science 2021-02-09 Jiawei Yang , Yuan Liang , Yao Zhang , Weinan Song , Kun Wang , Lei He

Complex nonlinear models such as deep neural network (DNNs) have become an important tool for image classification, speech recognition, natural language processing, and many other fields of application. These models however lack…

Advances in architectural design, data availability, and compute have driven remarkable progress in semantic segmentation. Yet, these models often rely on relaxed Bayesian assumptions, omitting critical uncertainty information needed for…

Computer Vision and Pattern Recognition · Computer Science 2026-02-19 M. M. A. Valiuddin , R. J. G. van Sloun , C. G. A. Viviers , P. H. N. de With , F. van der Sommen

Evaluation of predictive deep learning (DL) models beyond conventional performance metrics has become increasingly important for applications in sensitive environments like healthcare. Such models might have the capability to encode and…

Although deep learning (DL) models have shown great success in many medical image analysis tasks, deployment of the resulting models into real clinical contexts requires: (1) that they exhibit robustness and fairness across different…

Computer Vision and Pattern Recognition · Computer Science 2023-03-07 Raghav Mehta , Changjian Shui , Tal Arbel