Denis Huseljic

According to our database, Denis Huseljic authored at least 27 papers between 2017 and 2025.

Collaborative distances:

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

2025

Systematic Evaluation of Uncertainty Calibration in Pretrained Object Detectors.

Denis Huseljic, Marek Herde, Paul Hahn, Mehmet Muejde, Bernhard Sick

Int. J. Comput. Vis., March, 2025

2024

dopanim: A Dataset of Doppelganger Animals with Noisy Annotations from Multiple Humans.

Marek Herde, Denis Huseljic, Lukas Rauch, Bernhard Sick

Dataset, June, 2024

The Interplay of Uncertainty Modeling and Deep Active Learning: An Empirical Analysis in Image Classification.

Denis Huseljic, Marek Herde, Yannick Nagel, Lukas Rauch, Paulius Strimaitis, Bernhard Sick

Trans. Mach. Learn. Res., 2024

Fast Fishing: Approximating Bait for Efficient and Scalable Deep Active Image Classification.

Denis Huseljic, Paul Hahn, Marek Herde, Lukas Rauch, Bernhard Sick

Proceedings of the Machine Learning and Knowledge Discovery in Databases. Research Track, 2024

dopanim: A Dataset of Doppelganger Animals with Noisy Annotations from Multiple Humans.

Marek Herde, Denis Huseljic, Lukas Rauch, Bernhard Sick

Proceedings of the Advances in Neural Information Processing Systems 38: Annual Conference on Neural Information Processing Systems 2024, 2024

Towards Deep Active Learning in Avian Bioacoustics.

Lukas Rauch, Denis Huseljic, Moritz Wirth, Jens Decke, Bernhard Sick, Christoph Scholz

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), 2024

General Reusability: Ensuring Long-Term Benefits of Deep Active Learning.

Paul Hahn, Denis Huseljic, Marek Herde, Bernhard Sick

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), 2024

Annot-Mix: Learning with Noisy Class Labels from Multiple Annotators via a Mixup Extension.

Marek Herde, Lukas Lührs, Denis Huseljic, Bernhard Sick

Proceedings of the ECAI 2024 - 27th European Conference on Artificial Intelligence, 19-24 October 2024, Santiago de Compostela, Spain, 2024

2023

Multi-annotator Deep Learning: A Probabilistic Framework for Classification.

Marek Herde, Denis Huseljic, Bernhard Sick

Trans. Mach. Learn. Res., 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

ActiveGLAE: A Benchmark for Deep Active Learning with Transformers.

Lukas Rauch, Matthias Aßenmacher, Denis Huseljic, Moritz Wirth, Bernd Bischl, Bernhard Sick

Proceedings of the Machine Learning and Knowledge Discovery in Databases: Research Track, 2023

Role of Hyperparameters in Deep Active Learning.

Denis Huseljic, Marek Herde, Paul Hahn, Bernhard Sick

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 2023), 2023

Active Learning with Fast Model Updates and Class-Balanced Selection for Imbalanced Datasets.

Zhixin Huang, Yujiang He, Marek Herde, Denis Huseljic, Bernhard Sick

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 2023), 2023

Who knows best? A Case Study on Intelligent Crowdworker Selection via Deep Learning.

Marek Herde, Denis Huseljic, Bernhard Sick, Ulrich Bretschneider, Sarah Oeste-Reiß

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 2023), 2023

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 Review of Uncertainty Calibration in Pretrained Object Detectors.

Denis Huseljic, Marek Herde, Mehmet Muejde, Bernhard Sick

CoRR, 2022

Enhancing Active Learning with Weak Supervision and Transfer Learning by Leveraging Information and Knowledge Sources.

Lukas Rauch, Denis Huseljic, Bernhard Sick

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 2022), 2022

A Concept for Automated Polarized Web Content Annotation based on Multimodal Active Learning.

Marek Herde, Denis Huseljic, Jelena Mitrovic, Michael Granitzer, Bernhard Sick

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 2022), 2022

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

A Survey on Cost Types, Interaction Schemes, and Annotator Performance Models in Selection Algorithms for Active Learning in Classification.

Marek Herde, Denis Huseljic, Bernhard Sick, Adrian Calma

IEEE Access, 2021

A Concept for Highly Automated Pre-Labeling via Cross-Domain Label Transfer for Perception in Autonomous Driving.

Maarten Bieshaar, Marek Herde, Denis Huseljic, Bernhard Sick

Proceedings of the Workshop on Interactive Adaptive Learning (IAL 2021) co-located with the European Conference on Machine Learning and Principles and Practice of Knowledge Discovery in Databases (ECML PKDD 2021), 2021

Out-of-Distribution Detection and Generation Using Soft Brownian Offset Sampling and Autoencoders.

Felix Möller, Diego Botache, Denis Huseljic, Florian Heidecker, Maarten Bieshaar, Bernhard Sick

Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition Workshops, 2021

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

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

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