Search Results for author: Maciej Zięba

Found 16 papers, 11 papers with code

TreeFlow: Going beyond Tree-based Gaussian Probabilistic Regression

no code implementations8 Jun 2022 Patryk Wielopolski, Maciej Zięba

The tree-based ensembles are known for their outstanding performance for classification and regression problems characterized by feature vectors represented by mixed-type variables from various ranges and domains.

Continual learning on 3D point clouds with random compressed rehearsal

no code implementations16 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.

Continual Learning Visual Reasoning

Flow Plugin Network for conditional generation

1 code implementation7 Oct 2021 Patryk Wielopolski, Michał Koperski, Maciej Zięba

Generative models have gained many researchers' attention in the last years resulting in models such as StyleGAN for human face generation or PointFlow for the 3D point cloud generation.

Conditional Image Generation Face Generation +2

PluGeN: Multi-Label Conditional Generation From Pre-Trained Models

1 code implementation18 Sep 2021 Maciej Wołczyk, Magdalena Proszewska, Łukasz Maziarka, Maciej Zięba, Patryk Wielopolski, Rafał Kurczab, Marek Śmieja

Modern generative models achieve excellent quality in a variety of tasks including image or text generation and chemical molecule modeling.

Text Generation

RegFlow: Probabilistic Flow-based Regression for Future Prediction

no code implementations30 Nov 2020 Maciej Zięba, Marcin Przewięźlikowski, Marek Śmieja, Jacek Tabor, Tomasz Trzcinski, Przemysław Spurek

Predicting future states or actions of a given system remains a fundamental, yet unsolved challenge of intelligence, especially in the scope of complex and non-deterministic scenarios, such as modeling behavior of humans.

Future prediction

Representing Point Clouds with Generative Conditional Invertible Flow Networks

1 code implementation7 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.

Point Cloud Registration

UCSG-Net -- Unsupervised Discovering of Constructive Solid Geometry Tree

1 code implementation16 Jun 2020 Kacper Kania, Maciej Zięba, Tomasz Kajdanowicz

On the contrary, we propose a model that extracts a CSG parse tree without any supervision - UCSG-Net.

3D Shape Reconstruction

HyperFlow: Representing 3D Objects as Surfaces

1 code implementation15 Jun 2020 Przemysław Spurek, Maciej Zięba, Jacek Tabor, Tomasz Trzciński

To that end, we devise a generative model that uses a hypernetwork to return the weights of a Continuous Normalizing Flows (CNF) target network.

Autonomous Driving Quantization

Hypernetwork approach to generating point clouds

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.

Generating 3D Point Clouds

Conditional Invertible Flow for Point Cloud Generation

2 code implementations16 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.

Point Cloud Generation

Generative Adversarial Networks: recent developments

no code implementations16 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.

BIG-bench Machine Learning

Semi-supervised learning with Bidirectional GANs

no code implementations28 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.

General Classification Image Retrieval

Cannot find the paper you are looking for? You can Submit a new open access paper.