598 citations · 2.9k across the 89 of their papers we have counts for
7 papers · 1 filter
Analysis and Optimization of Loss Functions for Multiclass, Top-k, and Multilabel Classification
Maksim Lapin, Matthias Hein, Bernt Schiele
Top-k error is currently a popular performance measure on large scale image classification benchmarks such as ImageNet and Places. Despite its wide acceptance, our understanding of…
Globally Optimal Training of Generalized Polynomial Neural Networks with Nonlinear Spectral Methods
Antoine Gautier, Quynh Nguyen, Matthias Hein
The optimization problem behind neural networks is highly non-convex. Training with stochastic gradient descent and variants requires careful parameter tuning and provides no guara…
Improved Image Boundaries for Better Video Segmentation
Anna Khoreva, Rodrigo Benenson, Fabio Galasso +2
Graph-based video segmentation methods rely on superpixels as starting point. While most previous work has focused on the construction of the graph edges and weights as well as sol…
On the capillary self-focusing in a microfluidic system
M. Hein, R. Seemann, S. Afkhami
A computational framework is developed to address capillary self-focusing in Step Emulsification. The microfluidic system consists of a single shallow and wide microchannel that me…
Latent Embeddings for Zero-shot Classification
Yongqin Xian, Zeynep Akata, Gaurav Sharma +3
We present a novel latent embedding model for learning a compatibility function between image and class embeddings, in the context of zero-shot classification. The proposed method…
A nodal domain theorem and a higher-order Cheeger inequality for the graph -Laplacian
Francesco Tudisco, Matthias Hein
We consider the nonlinear graph -Laplacian and its set of eigenvalues and associated eigenfunctions of this operator defined by a variational principle. We prove a nodal domain…