Publications
Bayesian Prior Networks with PAC Training. arXiv preprint arXiv:1906.00816
(2019). Bolus arrival time estimation in dynamic contrast-enhanced magnetic resonance imaging of small animals based on spline models, in press. Physics in Medicine and Biology. 64
(2019). Content and Style Disentanglement for Artistic Style Transfer. Proceedings of the Intl. Conf. on Computer Vision (ICCV)
(2019). Deep Active Learning with Adaptive Acquisition. IJCAI. Proceedings, in press
(2019). Deep-Learning Jets with Uncertainties and More . arXiv preprint arXiv:1904.10004
(2019). Divide and Conquer the Embedding Space for Metric Learning. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR). https://github.com/CompVis/metric-learning-divide-and-conquer
(2019). An efficient algorithm for the piecewise affine-linear Mumford-Shah model based on a Taylor jet splitting. IEEE Transactions on Image Processing. 29
Technical Report (2.04 MB)
(2019). 
End-to-End Learned Random Walker for Seeded Image Segmentation. CVPR. Proceedings. 12559-12568
(2019). End-to-End Learning of Decision Trees and Forests. International Journal of Computer Vision. 1-15
(2019). ilastik: interactive machine learning for (bio)image analysis. Nature Methods
(2019). Instance Segmentation Via Associative Pixel Embeddings. Heidelberg University
(2019). Isotropic Reconstruction of Neural Morphology from Large Non-Isotropic 3D Electron MIcroscopy. Heidelberg University
(2019). LeMoNADe: Learned Motif and Neuronal Assembly Detection in calcium imaging videos. ICLR. Proceedings
(2019). A Meta-Transfer Objective for Learning to Disentangle Causal Mechanisms. arXiv preprint arXiv:1901.10912
Technical Report (871.59 KB)
(2019). 
MIC: Mining Interclass Characteristics for Improved Metric Learning. Proceedings of the Intl. Conf. on Computer Vision (ICCV)
(2019). Novel Machine Learning Approaches for Neurophysiological Data Analysis. Heidelberg University
(2019). Pipeline Für Die Automatisierte Objektsegmentierung Von 3D Lightshet Mikroskopiebildern. Heidelberg University
(2019). Robust Single Object Tracking Via Fully Convolutional Siamese Networks. Heidelberg University
(2019). Sampling-Free Variational Inference of Bayesian Neural Networks by Variance Backpropagation. UAI. Proceedings, in press
(2019). Semantic Instance Segmentation With The Multiway Mutex Watershed. Heidelberg University
(2019). Semi-Supervised Distance-Based Segmentation. Heidelberg University
(2019). Smoothing for signals with discontinuities using higher order Mumford-Shah models. Numerische Mathematik. 143(2) 423-460
Technical Report (1.09 MB)
(2019). 
Synaptic Cleft Prediction On Electron Microsope Images. Heidelberg University
(2019). Total variation regularization of pose signals with an application to 3D freehand ultrasound. IEEE Transactions on Medical Imaging. 38(10) 2245-2258
(2019). Unsupervised Part-Based Disentangling of Object Shape and Appearance. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (Oral + Best paper finalist: top 45 / 5160 submissions)
(2019). Unsupervised Representation Learning by Discovering Reliable Image Relations. Pattern Recognition. http://arxiv.org/abs/1911.07808
(2019). Unsupervised Robust Disentangling of Latent Characteristics for Image Synthesis. Proceedings of the Intl. Conf. on Computer Vision (ICCV). https://compvis.github.io/robust-disentangling/
(2019). Using a Transformation Content Block For Image Style Transfer. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR)
(2019). Weakly Supervised Learning of Dense SemanticCorrespondences and Segmentation. German Conference on Pattern Recognition (GCPR)
article (6.1 MB)
(2019). 
Weakly Supervised Semantic Segmentation. Heidelberg University
(2019). Attesting Similarity: Supporting the Organization and Study of Art Image Collections with Computer Vision. Digital Scholarship in the Humanities, Oxford University Press. 33 845-856
(2018). Augmented Reality Meets Computer Vision Efficient Data Generation for Urban Driving Scenes. IJCV. 1-12
Technical Report (3.83 MB)
(2018). 
Computer Vision und Kunstgeschichte — Dialog zweier Bildwissenschaften. Computing Art Reader: Einführung in die digitale Kunstgeschichte, P. Kuroczyński et al. (ed.)
413-17-83318-2-10-20181210.pdf (2.98 MB)
(2018). 
Cross and Learn: Cross-Modal Self-Supervision. German Conference on Pattern Recognition (GCPR) (Oral). Stuttgart, Germany. https://arxiv.org/abs/1811.03879v1
Article (891.47 KB)
Oral slides (9.17 MB)
(2018). 

Deep End-To-End Learning Of A Diffusion Process For Seeded Image Segmentation. Heidelberg University
(2018).