3 papers
cs.LG2022
Logarithmic Continual Learning
Wojciech Masarczyk, Paweł Wawrzyński, Daniel Marczak +2
We introduce a neural network architecture that logarithmically reduces the number of self-rehearsal steps in the generative rehearsal of continually learned models. In continual l…
cs.CV2021
EgoNN: Egocentric Neural Network for Point Cloud Based 6DoF Relocalization at the City Scale
Jacek Komorowski, Monika Wysoczanska, Tomasz Trzcinski
The paper presents a deep neural network-based method for global and local descriptors extraction from a point cloud acquired by a rotating 3D LiDAR. The descriptors can be used fo…
cs.LG2020
End-to-end Sinkhorn Autoencoder with Noise Generator
Kamil Deja, Jan Dubiński, Piotr Nowak +2
In this work, we propose a novel end-to-end sinkhorn autoencoder with noise generator for efficient data collection simulation. Simulating processes that aim at collecting experime…