Logo
User: Guest  Login
Authors:
Baumann, Anton; Roßberg, Thomas; Schmitt, Michael 
Document type:
Konferenzbeitrag / Conference Paper 
Title:
Probabilistic MIMO U-Net: Efficient and Accurate Uncertainty Estimation for Pixel-Wise Regression 
Title of conference publication:
2023 IEEE/CVF International Conference on Computer Vision Workshops (ICCVW) 
Conference title:
IEEE/CVF International Conference on Computer Vision Workshops (2023, Paris) 
Venue:
Paris 
Year of conference:
2023 
Date of conference beginning:
02.10.2023 
Date of conference ending:
03.10.2023 
Publishing institution:
IEEE Computer Society 
Year:
2023 
Pages from - to:
4500-4508 
Language:
Englisch 
Abstract:
Uncertainty estimation in machine learning is paramount for enhancing the reliability and interpretability of predictive models, especially in high-stakes real-world scenarios. Despite the availability of numerous methods, they often pose a trade-off between the quality of uncertainty estimation and computational efficiency. Addressing this challenge, we present an adaptation of the Multiple-Input Multiple-Output (MIMO) framework – an approach exploiting the overparameterization of deep neural n...    »
 
ISBN:
979-8-3503-0744-3 
Department:
Fakultät für Luft- und Raumfahrttechnik 
Institute:
LRT 9 - Institut für Raumfahrttechnik und Weltraumnutzung 
Chair:
Schmitt, Michael 
Open Access yes or no?:
Nein / No