Spremljaj
Julia Niebling
Julia Niebling
Researcher, DLR, Institute of Data Sciene
Preverjeni e-poštni naslov na dlr.de
Naslov
Navedeno
Navedeno
Leto
A branch--and--bound-based algorithm for nonconvex multiobjective optimization
J Niebling, G Eichfelder
SIAM Journal on Optimization 29 (1), 794-821, 2019
432019
Solving multiobjective mixed integer convex optimization problems
M De Santis, G Eichfelder, J Niebling, S Rocktäschel
SIAM Journal on Optimization 30 (4), 3122-3145, 2020
362020
Evaluation of multi feature fusion at score-level for appearance-based person re-identification
M Eisenbach, A Kolarow, A Vorndran, J Niebling, HM Gross
2015 international joint conference on neural networks (IJCNN), 1-8, 2015
312015
An algorithmic approach to multiobjective optimization with decision uncertainty
G Eichfelder, J Niebling, S Rocktäschel
Journal of Global Optimization 77 (1), 3-25, 2020
182020
Analysis of railway track irregularities with convolutional autoencoders and clustering algorithms
J Niebling, B Baasch, A Kruspe
Dependable Computing-EDCC 2020 Workshops: AI4RAILS, DREAMS, DSOGRI, SERENE …, 2020
62020
Nonconvex constrained optimization by a filtering branch and bound
G Eichfelder, K Klamroth, J Niebling
Journal of Global Optimization 80 (1), 31-61, 2021
42021
A branch-and-bound algorithm for biobjective problems
J Niebling, G Eichfelder
Proceedings of the XIII Global Optimization Workshop GOW16, 57-60, 2016
42016
Using a B&B algorithm from multiobjective optimization to solve constrained optimization problems
G Eichfelder, K Klamroth, J Niebling
AIP Conference Proceedings 2070 (1), 020028, 2019
22019
Analysing the Interactions Between Training Dataset Size, Label Noise and Model Performance in Remote Sensing Data
J Gütter, J Niebling, XX Zhu
IGARSS 2022-2022 IEEE International Geoscience and Remote Sensing Symposium …, 2022
12022
IS IT WORTH IT? COMPARING SIX DEEP AND CLASSICAL METHODS FOR UNSUPERVISED ANOMALY DETECTION IN TIME SERIES
F Rewicki, J Denzler, J Niebling
2023
Is it worth it? An experimental comparison of six deep-and classical machine learning methods for unsupervised anomaly detection in time series
F Rewicki, J Denzler, J Niebling
arXiv preprint arXiv:2212.11080, 2022
2022
Domain Shifts in Dermoscopic Datasets
S Chamarthi, K Fogelberg, J Niebling
2022
Robust Distribution-Shift Aware Sar-Optical data Fusion for Multi-Label Scene Classification
J Gawlikowski, S Saha, J Niebling, XX Zhu
IGARSS 2022-2022 IEEE International Geoscience and Remote Sensing Symposium …, 2022
2022
Impact of Training Set Size on the Ability of Deep Neural Networks to Deal with Omission Noise
JA Gütter, A Kruspe, XX Zhu, J Niebling
Frontiers in Remote Sensing, 2022
2022
A multiobjective view on creating counterfactual explanations for explaining uncertainty in machine learning
J Niebling
2022
Structuring Uncertainty for Fine-Grained Sampling in Stochastic Segmentation Networks
F Nussbaum, J Gawlikowski, J Niebling
Advances in Neural Information Processing Systems, 2022
2022
Using Predictive Uncertainty for Cleaning Noisy Annotations
JA Gütter, H Ulman, J Niebling
2022
Nonconvex and mixed integer multiobjective optimization with an application to decision uncertainty
J Niebling
Dissertation, Ilmenau, TU Ilmenau, 2019, 2019
2019
Ein Branch-and-Bound-Verfahren für bikriterielle Optimierungsprobleme
J Niebling
2015
Eigenvalue conditions for induced subgraphs
J Harant
Deutsche Nationalbibliothek, 2014
2014
Sistem trenutno ne more izvesti postopka. Poskusite znova pozneje.
Članki 1–20