• Publications
  • Influence
Ilastik: Interactive learning and segmentation toolkit
Segmentation is the process of partitioning digital images into meaningful regions. The analysis of biological high content images often requires segmentation as a first step. We propose ilastik asExpand
Essentially No Barriers in Neural Network Energy Landscape
Surprisingly, the paths between minima of recent neural network architectures on CIFAR10 and CIFar100 are essentially flat, which implies that neural networks have enough capacity for structural changes, or that these changes are small betweenMinima. Expand
Learning Steerable Filters for Rotation Equivariant CNNs
Steerable Filter CNNs (SFCNNs) are developed which achieve joint equivariance under translations and rotations by design and generalize He's weight initialization scheme to filters which are defined as a linear combination of a system of atomic filters. Expand
An Objective Comparison of Cell Tracking Algorithms
It is found that methods that either take prior information into account using learning strategies or analyze cells in a global spatiotemporal video context performed better than other methods under the segmentation and tracking scenarios included in the Cell Tracking Challenge. Expand
ilastik: interactive machine learning for (bio)image analysis
We present ilastik, an easy-to-use interactive tool that brings machine-learning-based (bio)image analysis to end users without substantial computational expertise. It contains pre-defined workflowsExpand
A Comparative Study of Modern Inference Techniques for Discrete Energy Minimization Problems
This study presents an empirical comparison of 24 state-of-art techniques on a corpus of 2,300 energy minimization instances from 20 diverse computer vision applications and suggests that polyhedral methods and integer programming solvers are competitive in terms of runtime and solution quality over a large range of model types. Expand
Learning to count with regression forest and structured labels
Using an ensemble of randomized regression trees that use dense features as input, this work obtains results that are of similar quality, at a fraction of the training time, and with low implementation effort. Expand
On the Spectral Bias of Neural Networks
This work shows that deep ReLU networks are biased towards low frequency functions, and studies the robustness of the frequency components with respect to parameter perturbation, to develop the intuition that the parameters must be finely tuned to express high frequency functions. Expand
Robust prediction of the MASCOT score for an improved quality assessment in mass spectrometric proteomics.
A continuous quality score is presented that can be computed very quickly and can be considered an approximation of the MASCOT score in case of a correct identification of proteins by tandem mass spectrometry. Expand