Marek Herde

38 papers A* 2A 1B 5Journal 20Unranked 9
YearRankTypeTitle / Venue / Authors
2026 J jnl
BoSS: A Best-of-Strategies Selector as an Oracle for Deep Active Learning.
CoRR
Denis Huseljic, Paul Hahn, Marek Herde, Christoph Sandrock, Bernhard Sick
2025 A* conf
BirdSet: A Large-Scale Dataset for Audio Classification in Avian Bioacoustics.
ICLR
Lukas Rauch, Raphael Schwinger, Moritz Wirth, René Heinrich, Denis Huseljic, Marek Herde, Jonas Lange, Stefan Kahl, Bernhard Sick, Sven Tomforde, Christoph Scholz
2025 J jnl
Cleaning the Pool: Progressive Filtering of Unlabeled Pools in Deep Active Learning.
CoRR
Denis Huseljic, Marek Herde, Lukas Rauch, Paul Hahn, Bernhard Sick
2025 — conf
Efficient Bayesian Updates for Deep Active Learning via Laplace Approximations.
ECML/PKDD (2)
Denis Huseljic, Marek Herde, Lukas Rauch, Paul Hahn, Zhixin Huang, Daniel Kottke, Stephan Vogt, Bernhard Sick
2025 J jnl
No Free Lunch in Active Learning: LLM Embedding Quality Dictates Query Strategy Success.
CoRR
Lukas Rauch, Moritz Wirth, Denis Huseljic, Marek Herde, Bernhard Sick, Matthias Aßenmacher
2025 J jnl
Systematic Evaluation of Uncertainty Calibration in Pretrained Object Detectors.
Int. J. Comput. Vis.
Denis Huseljic, Marek Herde, Paul Hahn, Mehmet Muejde, Bernhard Sick
2025 J jnl
crowd-hpo: Realistic Hyperparameter Optimization and Benchmarking for Learning from Crowds with Noisy Labels.
CoRR
Marek Herde, Lukas Lührs, Denis Huseljic, Bernhard Sick
2025 J jnl
crowd-hpo: Realistic Hyperparameter Optimization and Benchmarking for Learning from Crowds with Noisy Labels.
Trans. Mach. Learn. Res.
Marek Herde, Lukas Lührs, Denis Huseljic, Bernhard Sick
2024 A conf
Annot-Mix: Learning with Noisy Class Labels from Multiple Annotators via a Mixup Extension.
ECAI
Marek Herde, Lukas Lührs, Denis Huseljic, Bernhard Sick
2024 J jnl
Annot-Mix: Learning with Noisy Class Labels from Multiple Annotators via a Mixup Extension.
CoRR
Marek Herde, Lukas Lührs, Denis Huseljic, Bernhard Sick
2024 J jnl
Fast Fishing: Approximating BAIT for Efficient and Scalable Deep Active Image Classification.
CoRR
Denis Huseljic, Paul Hahn, Marek Herde, Lukas Rauch, Bernhard Sick
2024 — conf
Fast Fishing: Approximating Bait for Efficient and Scalable Deep Active Image Classification.
ECML/PKDD (7)
Denis Huseljic, Paul Hahn, Marek Herde, Lukas Rauch, Bernhard Sick
2024 — conf
General Reusability: Ensuring Long-Term Benefits of Deep Active Learning.
IAL@PKDD/ECML
Paul Hahn, Denis Huseljic, Marek Herde, Bernhard Sick
2024 — ed.
Proceedings of the Workshop on Interactive Adaptive Learning co-located with European Conference on Machine Learning and Principles and Practice of Knowledge Discovery in Databases (ECML-PKDD 2024), Vilnius, Lithuania, September 9th, 2024.
IAL@PKDD/ECML
Mirko Bunse, Marek Herde, Georg Krempl, Vincent Lemaire, Alaa Tharwat, Minh Tuan Pham, Amal Saadallah
2024 J jnl
The Interplay of Uncertainty Modeling and Deep Active Learning: An Empirical Analysis in Image Classification.
Trans. Mach. Learn. Res.
Denis Huseljic, Marek Herde, Yannick Nagel, Lukas Rauch, Paulius Strimaitis, Bernhard Sick
2024 — conf
Tutorial: Interactive Adaptive Learning.
IAL@PKDD/ECML
Marek Herde, Tuan Pham Minh, Alaa Tharwat, Bernhard Sick
2024 A* conf
dopanim: A Dataset of Doppelganger Animals with Noisy Annotations from Multiple Humans.
NeurIPS
Marek Herde, Denis Huseljic, Lukas Rauch, Bernhard Sick
2024 J jnl
dopanim: A Dataset of Doppelganger Animals with Noisy Annotations from Multiple Humans.
CoRR
Marek Herde, Denis Huseljic, Lukas Rauch, Bernhard Sick
2023 J jnl
Active Label Refinement for Semantic Segmentation of Satellite Images.
CoRR
Tuan Pham Minh, Jayan Wijesingha, Daniel Kottke, Marek Herde, Denis Huseljic, Bernhard Sick, Michael Wachendorf, Thomas Esch
2023 — conf
Active Learning with Fast Model Updates and Class-Balanced Selection for Imbalanced Datasets.
IAL@PKDD/ECML
Zhixin Huang, Yujiang He, Marek Herde, Denis Huseljic, Bernhard Sick
2023 B conf
Exploring the Potential of Optimal Active Learning via a Non-myopic Oracle Policy.
DS
Christoph Sandrock, Marek Herde, Daniel Kottke, Bernhard Sick
2023 J jnl
Multi-annotator Deep Learning: A Probabilistic Framework for Classification.
CoRR
Marek Herde, Denis Huseljic, Bernhard Sick
2023 J jnl
Multi-annotator Deep Learning: A Probabilistic Framework for Classification.
Trans. Mach. Learn. Res.
Marek Herde, Denis Huseljic, Bernhard Sick
2023 — conf
Role of Hyperparameters in Deep Active Learning.
IAL@PKDD/ECML
Denis Huseljic, Marek Herde, Paul Hahn, Bernhard Sick
2023 — conf
Who knows best? A Case Study on Intelligent Crowdworker Selection via Deep Learning.
IAL@PKDD/ECML
Marek Herde, Denis Huseljic, Bernhard Sick, Ulrich Bretschneider, Sarah Oeste-Reiß
2022 — conf
A Concept for Automated Polarized Web Content Annotation based on Multimodal Active Learning.
IAL@PKDD/ECML
Marek Herde, Denis Huseljic, Jelena Mitrovic, Michael Granitzer, Bernhard Sick
2022 J jnl
A Review of Uncertainty Calibration in Pretrained Object Detectors.
CoRR
Denis Huseljic, Marek Herde, Mehmet Muejde, Bernhard Sick
2022 J jnl
Fast Bayesian Updates for Deep Learning with a Use Case in Active Learning.
CoRR
Marek Herde, Zhixin Huang, Denis Huseljic, Daniel Kottke, Stephan Vogt, Bernhard Sick
2021 — conf
A Concept for Highly Automated Pre-Labeling via Cross-Domain Label Transfer for Perception in Autonomous Driving.
IAL@PKDD/ECML
Maarten Bieshaar, Marek Herde, Denis Huseljic, Bernhard Sick
2021 J jnl
A Survey on Cost Types, Interaction Schemes, and Annotator Performance Models in Selection Algorithms for Active Learning in Classification.
IEEE Access
Marek Herde, Denis Huseljic, Bernhard Sick, Adrian Calma
2021 J jnl
A Survey on Cost Types, Interaction Schemes, and Annotator Performance Models in Selection Algorithms for Active Learning in Classification.
CoRR
Marek Herde, Denis Huseljic, Bernhard Sick, Adrian Calma
2021 J jnl
Toward optimal probabilistic active learning using a Bayesian approach.
Mach. Learn.
Daniel Kottke, Marek Herde, Christoph Sandrock, Denis Huseljic, Georg Krempl, Bernhard Sick
2020 B conf
Multi-Annotator Probabilistic Active Learning.
ICPR
Marek Herde, Daniel Kottke, Denis Huseljic, Bernhard Sick
2020 B conf
Separation of Aleatoric and Epistemic Uncertainty in Deterministic Deep Neural Networks.
ICPR
Denis Huseljic, Bernhard Sick, Marek Herde, Daniel Kottke
2020 J jnl
Toward Optimal Probabilistic Active Learning Using a Bayesian Approach.
CoRR
Daniel Kottke, Marek Herde, Christoph Sandrock, Denis Huseljic, Georg Krempl, Bernhard Sick
2019 J jnl
Collaborative Interactive Learning - A clarification of terms and a differentiation from other research fields.
CoRR
Tom Hanika, Marek Herde, Jochen Kuhn, Jan Marco Leimeister, Paul Lukowicz, Sarah Oeste-Reiß, Albrecht Schmidt, Bernhard Sick, Gerd Stumme, Sven Tomforde, Katharina Anna Zweig
2019 B conf
Combining Self-reported Confidences from Uncertain Annotators to Improve Label Quality.
IJCNN
Christoph Sandrock, Marek Herde, Adrian Calma, Daniel Kottke, Bernhard Sick
2018 B conf
Active Sorting - An Efficient Training of a Sorting Robot with Active Learning Techniques.
IJCNN
Marek Herde, Daniel Kottke, Adrian Calma, Maarten Bieshaar, Stephan Deist, Bernhard Sick