D
Daniel Cremers
Researcher at Technische Universität München
Publications - 702
Citations - 55592
Daniel Cremers is an academic researcher from Technische Universität München. The author has contributed to research in topics: Image segmentation & Computer science. The author has an hindex of 99, co-authored 655 publications receiving 44957 citations. Previous affiliations of Daniel Cremers include Siemens & University of Mannheim.
Papers
More filters
Posted Content
Co-Sparse Textural Similarity for Image Segmentation
TL;DR: An algorithm for segmenting natural images based on texture and color information, which leverages the co-sparse analysis model for image segmentation within a convex multilabel optimization framework is proposed, which outperforms state-of-the-art interactive segmentation methods on the Graz Benchmark.
Posted Content
Probabilistic Discriminative Learning with Layered Graphical Models
TL;DR: This work designs layered graphical models (LGMs) in close analogy to neural networks, that is, they have deep hierarchical structures and convolutional or local connections between layers and can be efficiently trained via backpropagation on mainstream deep learning frameworks such as PyTorch.
Proceedings ArticleDOI
3D Deep Learning for Biological Function Prediction from Physical Fields
Vladimir Golkov,Marcin J. Skwark,Atanas Mirchev,Georgi Dikov,Alexander R. Geanes,Jeffrey L. Mendenhall,Jens Meiler,Daniel Cremers +7 more
TL;DR: In this paper, deep learning can predict biological function of molecules directly from their raw 3D approximated electron density and electrostatic potential fields, based on which proteins or drugs-like compounds can fit to binding partners.
Book ChapterDOI
Performance Evaluation of Narrow Band Methods for Variational Stereo Reconstruction
TL;DR: In this article, a narrow band formulation of variational multilabel optimization is proposed to reduce memory and computation time by orders of magnitude while preserving almost the same quality of results.
Posted Content
Effective Version Space Reduction for Convolutional Neural Networks
TL;DR: This work identifies the connection between two approaches---prior mass reduction and diameter reduction---and proposes a new diameter-based querying method---the minimum Gibbs-vote disagreement, and illustrates how version space of neural networks evolves and examines the realizability assumption.