Daniel Kottke

According to our database, Daniel Kottke authored at least 30 papers between 2014 and 2023.

Collaborative distances:

• Dijkstra number of four.
• Erdős number of four.

2023

Active Label Refinement for Semantic Segmentation of Satellite Images.

Tuan Pham Minh, Jayan Wijesingha, Daniel Kottke, Marek Herde, Denis Huseljic, Bernhard Sick, Michael Wachendorf, Thomas Esch

CoRR, 2023

Exploring the Potential of Optimal Active Learning via a Non-myopic Oracle Policy.

Christoph Sandrock, Marek Herde, Daniel Kottke, Bernhard Sick

Proceedings of the Discovery Science - 26th International Conference, 2023

2022

Stream-based active learning for sliding windows under the influence of verification latency.

Tuan Pham, Daniel Kottke, Georg Krempl, Bernhard Sick

Mach. Learn., 2022

Efficient SVDD sampling with approximation guarantees for the decision boundary.

Adrian Englhardt, Holger Trittenbach, Daniel Kottke, Bernhard Sick, Klemens Böhm

Mach. Learn., 2022

Fast Bayesian Updates for Deep Learning with a Use Case in Active Learning.

Marek Herde, Zhixin Huang, Denis Huseljic, Daniel Kottke, Stephan Vogt, Bernhard Sick

CoRR, 2022

A Stopping Criterion for Transductive Active Learning.

Daniel Kottke, Christoph Sandrock, Georg Krempl, Bernhard Sick

Proceedings of the Machine Learning and Knowledge Discovery in Databases, 2022

2021

Ein holistischer Ansatz für Pool-basiertes Aktives Lernen.

Daniel Kottke

Proceedings of the Ausgezeichnete Informatikdissertationen 2021., 2021

A holistic, decision-theoretic framework for pool-based active learning.

Daniel Kottke

PhD thesis, 2021

Toward optimal probabilistic active learning using a Bayesian approach.

Daniel Kottke, Marek Herde, Christoph Sandrock, Denis Huseljic, Georg Krempl, Bernhard Sick

Mach. Learn., 2021

ACE: A Novel Approach for the Statistical Analysis of Pairwise Connectivity.

Georg Krempl, Daniel Kottke, Tuan Pham Minh

CoRR, 2021

Probabilistic Active Learning for Active Class Selection.

Daniel Kottke, Georg Krempl, Marianne Stecklina, Cornelius Styp von Rekowski, Tim Sabsch, Tuan Pham Minh, Matthias Deliano, Myra Spiliopoulou, Bernhard Sick

CoRR, 2021

Statistical Analysis of Pairwise Connectivity.

Georg Krempl, Daniel Kottke, Tuan Pham

Proceedings of the Discovery Science - 24th International Conference, 2021

2020

Improving Self-Adaptation For Multi-Sensor Activity Recognition with Active Learning.

Tuan Pham Minh, Daniel Kottke, Anna Tsarenko, Christian Gruhl, Bernhard Sick

Proceedings of the 2020 International Joint Conference on Neural Networks, 2020

Separation of Aleatoric and Epistemic Uncertainty in Deterministic Deep Neural Networks.

Denis Huseljic, Bernhard Sick, Marek Herde, Daniel Kottke

Proceedings of the 25th International Conference on Pattern Recognition, 2020

Multi-Annotator Probabilistic Active Learning.

Marek Herde, Daniel Kottke, Denis Huseljic, Bernhard Sick

Proceedings of the 25th International Conference on Pattern Recognition, 2020

2019

Limitations of Assessing Active Learning Performance at Runtime.

Daniel Kottke, Jim Schellinger, Denis Huseljic, Bernhard Sick

CoRR, 2019

Combining Self-reported Confidences from Uncertain Annotators to Improve Label Quality.

Christoph Sandrock, Marek Herde, Adrian Calma, Daniel Kottke, Bernhard Sick

Proceedings of the International Joint Conference on Neural Networks, 2019

2018

The Other Human in The Loop - A Pilot Study to Find Selection Strategies for Active Learning.

Daniel Kottke, Adrian Calma, Denis Huseljic, Christoph Sandrock, George Kachergis, Bernhard Sick

Proceedings of the 2018 International Joint Conference on Neural Networks, 2018

Active Sorting - An Efficient Training of a Sorting Robot with Active Learning Techniques.

Marek Herde, Daniel Kottke, Adrian Calma, Maarten Bieshaar, Stephan Deist, Bernhard Sick

Proceedings of the 2018 International Joint Conference on Neural Networks, 2018

Active Learning With Realistic Data - A Case Study.

Adrian Calma, Moritz Stolz, Daniel Kottke, Sven Tomforde, Bernhard Sick

Proceedings of the 2018 International Joint Conference on Neural Networks, 2018

2017

Learning to Learn: Dynamic Runtime Exploitation of Various Knowledge Sources and Machine Learning Paradigms.

Adrian Calma, Daniel Kottke, Bernhard Sick, Sven Tomforde

Proceedings of the 2nd IEEE International Workshops on Foundations and Applications of Self* Systems, 2017

Probabilistic Active Learning with Structure-Sensitive Kernels.

Dominik Lang, Daniel Kottke, Georg Krempl

Proceedings of the Workshop and Tutorial on Interactive Adaptive Learning co-located with European Conference on Machine Learning and Principles and Practice of Knowledge Discovery in Databases (ECML PKDD 2017), 2017

Challenges of Reliable, Realistic and Comparable Active Learning Evaluation.

Daniel Kottke, Adrian Calma, Denis Huseljic, Georg Krempl, Bernhard Sick

Proceedings of the Workshop and Tutorial on Interactive Adaptive Learning co-located with European Conference on Machine Learning and Principles and Practice of Knowledge Discovery in Databases (ECML PKDD 2017), 2017

2016

Investigating Exploratory Capabilities of Uncertainty Sampling using SVMs in Active Learning.

Dominik Lang, Daniel Kottke, Georg Krempl, Myra Spiliopoulou

Proceedings of the Workshop on Active Learning: Applications, 2016

Multi-Class Probabilistic Active Learning.

Daniel Kottke, Georg Krempl, Dominik Lang, Johannes Teschner, Myra Spiliopoulou

Proceedings of the ECAI 2016 - 22nd European Conference on Artificial Intelligence, 29 August-2 September 2016, The Hague, The Netherlands, 2016

2015

Optimised probabilistic active learning (OPAL) - For fast, non-myopic, cost-sensitive active classification.

Georg Krempl, Daniel Kottke, Vincent Lemaire

Mach. Learn., 2015

Probabilistic Active Learning in Datastreams.

Daniel Kottke, Georg Krempl, Myra Spiliopoulou

Proceedings of the Advances in Intelligent Data Analysis XIV, 2015

Data-Driven Spine Detection for Multi-Sequence MRI.

Daniel Kottke, Gino Gulamhussene, Klaus D. Tönnies

Proceedings of the Bildverarbeitung für die Medizin 2015, Algorithmen - Systeme, 2015

2014

Probabilistic Active Learning: A Short Proposition.

Georg Krempl, Daniel Kottke, Myra Spiliopoulou

Proceedings of the ECAI 2014 - 21st European Conference on Artificial Intelligence, 18-22 August 2014, Prague, Czech Republic, 2014

Probabilistic Active Learning: Towards Combining Versatility, Optimality and Efficiency.

Georg Krempl, Daniel Kottke, Myra Spiliopoulou

Proceedings of the Discovery Science - 17th International Conference, 2014