• Publications
  • Influence
Distortion Invariant Object Recognition in the Dynamic Link Architecture
TLDR
An object recognition system based on the dynamic link architecture, an extension to classical artificial neural networks (ANNs), is presented. Expand
  • 2,028
  • 108
  • PDF
Stability-Based Validation of Clustering Solutions
TLDR
We introduce a measure of cluster stability to assess the validity of a cluster model. Expand
  • 439
  • 39
The Balanced Accuracy and Its Posterior Distribution
TLDR
Evaluating the performance of a classification algorithm critically requires a measure of the degree to which unseen examples have been identified with their correct class labels. Expand
  • 648
  • 38
  • PDF
Weakly supervised semantic segmentation with a multi-image model
TLDR
We propose a novel method for weakly supervised semantic segmentation, where one has to predict a label for every pixel in the training images. Expand
  • 163
  • 31
  • PDF
Guaranteed Non-convex Optimization: Submodular Maximization over Continuous Domains
TLDR
An extended version containing further details is at http://arxiv.org/abs/1606.05615.Submodular continuous functions are a category of (generally) non-convex/non-concave functions with a wide spectrum of applications. Expand
  • 88
  • 28
  • PDF
Highly multiplexed imaging of tumor tissues with subcellular resolution by mass cytometry
Mass cytometry enables high-dimensional, single-cell analysis of cell type and state. In mass cytometry, rare earth metals are used as reporters on antibodies. Analysis of metal abundances using theExpand
  • 687
  • 27
  • PDF
Empirical evaluation of dissimilarity measures for color and texture
TLDR
This paper empirically compares nine image dissimilarity measures that are based on distributions of color and texture features summarizing over 1,000 CPU hours of computational experiments. Expand
  • 547
  • 26
  • PDF
Pairwise Data Clustering by Deterministic Annealing
TLDR
A new structure-preserving algorithm to cluster dissimilarity data and to simultaneously embed these data in a Euclidian vector space is discussed which can be used for dimensionality reduction and data visualization. Expand
  • 528
  • 26
  • PDF
Crowdsourcing the creation of image segmentation algorithms for connectomics
TLDR
We propose a solution to this problem, which should be useful for a future 3D segmentation challenge. Expand
  • 207
  • 24
  • PDF
Optimal Cluster Preserving Embedding of Nonmetric Proximity Data
TLDR
We show that all clustering methods, which are invariant under additive shifts of the pairwise proximities, can be reformulated as grouping problems in Euclidian spaces. Expand
  • 196
  • 20
  • PDF