26 citations · 28 across the 2 of their papers we have counts for
3 papers
RECALL: Rehearsal-free Continual Learning for Object Classification
Markus Knauer, Maximilian Denninger, Rudolph Triebel
Convolutional neural networks show remarkable results in classification but struggle with learning new things on the fly. We present a novel rehearsal-free approach, where a deep n…
Learning to Localize in New Environments from Synthetic Training Data
Dominik Winkelbauer, Maximilian Denninger, Rudolph Triebel
Most existing approaches for visual localization either need a detailed 3D model of the environment or, in the case of learning-based methods, must be retrained for each new scene.…
BlenderProc
Maximilian Denninger, Martin Sundermeyer, Dominik Winkelbauer +5
BlenderProc is a modular procedural pipeline, which helps in generating real looking images for the training of convolutional neural networks. These can be used in a variety of use…