85 citations · 103 across the 3 of their papers we have counts for
3 papers
GGNN: Graph-based GPU Nearest Neighbor Search
Fabian Groh, Lukas Ruppert, Patrick Wieschollek +1
Approximate nearest neighbor (ANN) search in high dimensions is an integral part of several computer vision systems and gains importance in deep learning with explicit memory repre…
Flex-Convolution (Million-Scale Point-Cloud Learning Beyond Grid-Worlds)
Fabian Groh, Patrick Wieschollek, Hendrik P. A. Lensch
Traditional convolution layers are specifically designed to exploit the natural data representation of images -- a fixed and regular grid. However, unstructured data like 3D point…
Backpropagation Training for Fisher Vectors within Neural Networks
Patrick Wieschollek, Fabian Groh, Hendrik P. A. Lensch
Fisher-Vectors (FV) encode higher-order statistics of a set of multiple local descriptors like SIFT features. They already show good performance in combination with shallow learnin…