54 citations · 164 across the 23 of their papers we have counts for
26 papers
Classical Out-of-Distribution Detection Methods Benchmark in Text Classification Tasks
Mateusz Baran, Joanna Baran, Mateusz Wójcik +2
State-of-the-art models can perform well in controlled environments, but they often struggle when presented with out-of-distribution (OOD) examples, making OOD detection a critical…
Self-supervised adversarial masking for 3D point cloud representation learning
Michał Szachniewicz, Wojciech Kozłowski, Michał Stypułkowski +1
Self-supervised methods have been proven effective for learning deep representations of 3D point cloud data. Although recent methods in this domain often rely on random masking of…
MultiPlaneNeRF: Neural Radiance Field with Non-Trainable Representation
Dominik Zimny, Artur Kasymov, Adam Kania +4
NeRF is a popular model that efficiently represents 3D objects from 2D images. However, vanilla NeRF has some important limitations. NeRF must be trained on each object separately.…
NeRFlame: FLAME-based conditioning of NeRF for 3D face rendering
Wojciech Zając, Joanna Waczyńska, Piotr Borycki +3
Traditional 3D face models are based on mesh representations with texture. One of the most important models is FLAME (Faces Learned with an Articulated Model and Expressions), whic…
HyperNeRFGAN: Hypernetwork approach to 3D NeRF GAN
Adam Kania, Artur Kasymov, Jakub Kościukiewicz +4
The recent surge in popularity of deep generative models for 3D objects has highlighted the need for more efficient training methods, particularly given the difficulties associated…
Diffused Heads: Diffusion Models Beat GANs on Talking-Face Generation
Michał Stypułkowski, Konstantinos Vougioukas, Sen He +3
Talking face generation has historically struggled to produce head movements and natural facial expressions without guidance from additional reference videos. Recent developments i…
Two-headed eye-segmentation approach for biometric identification
Wiktor Lazarski, Maciej Zieba, Tanguy Jeanneau +2
Iris-based identification systems are among the most popular approaches for person identification. Such systems require good-quality segmentation modules that ideally identify the…
TreeFlow: Going beyond Tree-based Gaussian Probabilistic Regression
Patryk Wielopolski, Maciej Zięba
The tree-based ensembles are known for their outstanding performance in classification and regression problems characterized by feature vectors represented by mixed-type variables…
Continual learning on 3D point clouds with random compressed rehearsal
Maciej Zamorski, Michał Stypułkowski, Konrad Karanowski +2
Contemporary deep neural networks offer state-of-the-art results when applied to visual reasoning, e.g., in the context of 3D point cloud data. Point clouds are important datatype…
HyperMAML: Few-Shot Adaptation of Deep Models with Hypernetworks
M. Przewięźlikowski, P. Przybysz, J. Tabor +2
The aim of Few-Shot learning methods is to train models which can easily adapt to previously unseen tasks, based on small amounts of data. One of the most popular and elegant Few-S…
HyperShot: Few-Shot Learning by Kernel HyperNetworks
Marcin Sendera, Marcin Przewięźlikowski, Konrad Karanowski +3
Few-shot models aim at making predictions using a minimal number of labeled examples from a given task. The main challenge in this area is the one-shot setting where only one eleme…
Non-Gaussian Gaussian Processes for Few-Shot Regression
Marcin Sendera, Jacek Tabor, Aleksandra Nowak +5
Gaussian Processes (GPs) have been widely used in machine learning to model distributions over functions, with applications including multi-modal regression, time-series prediction…
Flow Plugin Network for conditional generation
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 gener…
PluGeN: Multi-Label Conditional Generation From Pre-Trained Models
Maciej Wołczyk, Magdalena Proszewska, Łukasz Maziarka +4
Modern generative models achieve excellent quality in a variety of tasks including image or text generation and chemical molecule modeling. However, existing methods often lack the…
Modeling 3D Surface Manifolds with a Locally Conditioned Atlas
Przemysław Spurek, Sebastian Winczowski, Maciej Zięba +3
Recently proposed 3D object reconstruction methods represent a mesh with an atlas - a set of planar patches approximating the surface. However, their application in a real-world sc…
RegFlow: Probabilistic Flow-based Regression for Future Prediction
Maciej Zięba, Marcin Przewięźlikowski, Marek Śmieja +3
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 scenar…
Representing Point Clouds with Generative Conditional Invertible Flow Networks
Michał Stypułkowski, Kacper Kania, Maciej Zamorski +3
In this paper, we propose a simple yet effective method to represent point clouds as sets of samples drawn from a cloud-specific probability distribution. This interpretation match…
HyperFlow: Representing 3D Objects as Surfaces
Przemysław Spurek, Maciej Zięba, Jacek Tabor +1
In this work, we present HyperFlow - a novel generative model that leverages hypernetworks to create continuous 3D object representations in a form of lightweight surfaces (meshes)…
UCSG-Net -- Unsupervised Discovering of Constructive Solid Geometry Tree
Kacper Kania, Maciej Zięba, Tomasz Kajdanowicz
Signed distance field (SDF) is a prominent implicit representation of 3D meshes. Methods that are based on such representation achieved state-of-the-art 3D shape reconstruction qua…
Hypernetwork approach to generating point clouds
Przemysław Spurek, Sebastian Winczowski, Jacek Tabor +3
In this work, we propose a novel method for generating 3D point clouds that leverage properties of hyper networks. Contrary to the existing methods that learn only the representati…
Conditional Invertible Flow for Point Cloud Generation
Michał Stypułkowski, Maciej Zamorski, Maciej Zięba +1
This paper focuses on a novel generative approach for 3D point clouds that makes use of invertible flow-based models. The main idea of the method is to treat a point cloud as a pro…
Generative Adversarial Networks: recent developments
Maciej Zamorski, Adrian Zdobylak, Maciej Zięba +1
In traditional generative modeling, good data representation is very often a base for a good machine learning model. It can be linked to good representations encoding more explanat…
Semi-supervised learning with Bidirectional GANs
Maciej Zamorski, Maciej Zięba
In this work we introduce a novel approach to train Bidirectional Generative Adversarial Model (BiGAN) in a semi-supervised manner. The presented method utilizes triplet loss funct…
Adversarial Autoencoders for Compact Representations of 3D Point Clouds
Maciej Zamorski, Maciej Zięba, Piotr Klukowski +4
Deep generative architectures provide a way to model not only images but also complex, 3-dimensional objects, such as point clouds. In this work, we present a novel method to obtai…