no code implementations • 16 May 2022 • Maciej Zamorski, Michał Stypułkowski, Konrad Karanowski, Tomasz Trzciński, Maciej Zięba
By using rehearsal and reconstruction as regularization methods of the learning process, our approach achieves a significant decrease of catastrophic forgetting compared to the existing solutions on several most popular point cloud datasets considering two continual learning settings: when a task is known beforehand, and in the challenging scenario of when task information is unknown to the model.
1 code implementation • 7 Oct 2020 • Michał Stypułkowski, Kacper Kania, Maciej Zamorski, Maciej Zięba, Tomasz Trzciński, Jan Chorowski
To exploit similarities between same-class objects and to improve model performance, we turn to weight sharing: networks that model densities of points belonging to objects in the same family share all parameters with the exception of a small, object-specific embedding vector.
2 code implementations • ICML 2020 • Przemysław Spurek, Sebastian Winczowski, Jacek Tabor, Maciej Zamorski, Maciej Zięba, Tomasz Trzciński
The main idea of our HyperCloud method is to build a hyper network that returns weights of a particular neural network (target network) trained to map points from a uniform unit ball distribution into a 3D shape.
2 code implementations • 16 Oct 2019 • Michał Stypułkowski, Maciej Zamorski, Maciej Zięba, Jan Chorowski
This paper focuses on a novel generative approach for 3D point clouds that makes use of invertible flow-based models.
no code implementations • 16 Mar 2019 • Maciej Zamorski, Adrian Zdobylak, Maciej Zięba, Jerzy Świątek
In traditional generative modeling, good data representation is very often a base for a good machine learning model.
no code implementations • 28 Nov 2018 • Maciej Zamorski, Maciej Zięba
In this work we introduce a novel approach to train Bidirectional Generative Adversarial Model (BiGAN) in a semi-supervised manner.
4 code implementations • 19 Nov 2018 • Maciej Zamorski, Maciej Zięba, Piotr Klukowski, Rafał Nowak, Karol Kurach, Wojciech Stokowiec, Tomasz Trzciński
Deep generative architectures provide a way to model not only images but also complex, 3-dimensional objects, such as point clouds.