Axthelm, R., Luppold S., & Moroff M. (2022).  Crowd Management in der Lehre. Seamless Learning, Grenz- und kontextübergreifendes Lehren und Lernen in der Bodenseeregion. 123-132.

• BibTeX

Hermann, M., Dold D., Umlauf G., & Dürr O. (2022).  DeepDoubt - Improving uncertainty measures in machine learning to improve explainability and transparency. 2022 All-Hands-Meeting of the BMBF-funded AI Research Projects at Munich Center for Machine Learning.

• BibTeX

AHM2022_DeepDoubt.pdf (238.98 KB)

Hermann, M., Umlauf G., Goldlücke B., & Franz M. O. (2022).  Fast and efficient image novelty detection based on mean-shifts. Sensors | Unusual Behavior Detection Based on Machine Learning .

• BibTeX

Hermann, M., Umlauf G., & Franz M. (2022).  Fast and memory-efficient independent component analysis using Lie group techniques. International Conference on Curves and Surfaces.

• BibTeX

Hermann, M., Goldlücke B., & Franz M. O. (2022).  Image novelty detection based on mean-shift and typical set size. 21th International Conference on Image Analysis and Processing, ICIAP.

• BibTeX

ICIAP-mean-shift-novelty-detection-preprint.pdf (2.96 MB)

Hermann, M., Umlauf G., & Franz M. O. (2022).  Large-scale independent component analysis by speeding up Lie group techniques. International Conference on Acoustics, Speech, and Signal Processing, ICASSP.

• BibTeX

conference_101719.pdf (646.58 KB)

Axthelm, R. (2022).  Mathematik mit digitalen Bildern sichtbar machen. Seamless Learning, Grenz- und kontextübergreifendes Lehren und Lernen in der Bodenseeregion. 133-145.

• BibTeX

Hermann, M., Griesser D., Gundel B., Dold D., Umlauf G., & Franz M. O. (2022).  Targetless Lidar-camera registration using patch-wise mutual information. International Conference on Information Fusion.

• BibTeX

mir_reg_patch.pdf (9.58 MB)

Scharpf, P., Hong C. Lap, & Duerr O. (2021).  Accelerating Active Learning Image Labeling Through Bulk Shift Recommendations. 2021 International Conference on Data Mining Workshops (ICDMW). 398-404.

• BibTeX

Grunwald, M., Hermann M., Freiberg F., & Franz M. O. (2021).  Biologically-inspired vs. CNN texture representations in novelty detection. Applications of Machine Learning 2021. 118430I.

• BibTeX

Spie2021.pdf (5.33 MB)

Sick, B., Hothorn T., & Dürr O. (2021).  Deep transformation models: Tackling complex regression problems with neural network based transformation models. Accepted for Proceedings of the 25th International Conference on Pattern Recognition (ICPR), Milan/Online, 2021.

• BibTeX

Arpogaus, M., Voß M., Sick B., Nigge-Uricher M., & Dürr O. (2021).  Probabilistic Short-Term Low-Voltage Load Forecasting using Bernstein-Polynomial Normalizing Flows. ICML 2021, Workshop Tackling Climate Change with Machine Learning, June 26, 2021, virtual.

• BibTeX

Arpogaus2021_Probabilistic_Forecasting.pdf (427.35 KB)

Hörtling, S., Dold D., Dürr O., & Sick B. (2021).  Transformation models for flexible posteriors in variational bayes. arXiv preprint. 2106.00528.

• BibTeX

2106.00528.pdf (1.03 MB)

Griesser, D., Dold D., Umlauf G., & Franz M.O. (2020).  CNN-Based Monocular 3D Ship Detection Using Inverse Perspective. Global Oceans.

• BibTeX

Hake, F., Hermann M., Alkhatib H., Hesse C., Holste K., Umlauf G., et al. (2020).  Damage Detection for Port Infrastructure by Means of Machine-Learning-Algorithms. FIG Working Week 2020.

• BibTeX

Fig2020.pdf (876.57 KB)

Kook, L., Herzog L., Hothorn T., Dürr O., & Sick B. (2020).  Deep and interpretable regression models for ordinal outcomes. arXiv preprint. 2010.08376.

• BibTeX

Pearse, G. D., Tan A. Y. S., Watt M. S., Franz M. O., & Dash J. P. (2020).  Detecting and mapping tree seedlings in UAV imagery using convolutional neural networks and field-verified data. ISPRS Journal of Photogrammetry and Remote Sensing. 168, 156 - 169.

• BibTeX

Herzog, L., Murina E., Dürr O., Wegener S., & Sick B. (2020).  Integrating uncertainty in deep neural networks for MRI based stroke analysis. Medical Image Analysis. 65, 101790.

• BibTeX

Kook, L., Herzog L., Hothorn T., Dürr O., & Sick B. (2020).  Ordinal neural network transformation models: deep and interpretable regression models for ordinal outcomes. arXiv e-prints. 2010.08376.

• BibTeX

Dürr, O., Sick B., & Murina E. (2020).  Probabilistic Deep Learning: With Python, Keras and TensorFlow Probability.

• BibTeX

Brach, K., Sick B., & Dürr O. (2020).  Single Shot MC Dropout Approximation. ICML Workshop on Uncertainty and Robustness in Deep Learning.

• BibTeX

Stadelmann, T., Tolkachev V., Sick B., & Dürr O. (2019).  Beyond ImageNet: Deep Learning in Industrial Practice. Applied Data Science. 205-232.

• BibTeX

Rohrbach, J., Rainhard T., Sick B., & Dürr O. (2019).  Bone erosion scoring for rheumatoid arthritis with deep convolutional neural networks.

• BibTeX

Schall, M., Schambach M-P., & Franz M. O. (2019).  Dissecting Multi-Line Handwriting for Multi-Dimensional Connectionist Classification. 15th IAPR International Conference on Document Analysis and Recognition.

• BibTeX

Dissecting Multi-Line Handwriting for Multi-Dimensional Connectionist Classification.pdf (553.24 KB)

Schambach, M-P., von der Nüll S., & Schall M. (2019).  Fast and Reliable Acquisition of Truth Data for Document Analysis using Cyclic Suggest Algorithms. ICDAR-OST: The 2nd International Workshop on Open Services and Tools for Document Analysis.

• BibTeX

Fast and Reliable Acquisition of Truth Data for Document Analysis using Cyclic Suggest Algorithms.pdf (776.45 KB)