Search Results for author: Przemysław Spurek

Found 46 papers, 30 papers with code

Introduction to Cross-Entropy Clustering The R Package CEC

no code implementations19 Aug 2015 Jacek Tabor, Przemysław Spurek, Konrad Kamieniecki, Marek Śmieja, Krzysztof Misztal

The R Package CEC performs clustering based on the cross-entropy clustering (CEC) method, which was recently developed with the use of information theory.

Clustering

Processing of missing data by neural networks

1 code implementation NeurIPS 2018 Marek Smieja, Łukasz Struski, Jacek Tabor, Bartosz Zieliński, Przemysław Spurek

We propose a general, theoretically justified mechanism for processing missing data by neural networks.

Imputation

Cramer-Wold AutoEncoder

2 code implementations ICLR 2019 Szymon Knop, Jacek Tabor, Przemysław Spurek, Igor Podolak, Marcin Mazur, Stanisław Jastrzębski

The crucial new ingredient is the introduction of a new (Cramer-Wold) metric in the space of densities, which replaces the Wasserstein metric used in SWAE.

Deep processing of structured data

no code implementations27 Sep 2018 Łukasz Maziarka, Marek Śmieja, Aleksandra Nowak, Jacek Tabor, Łukasz Struski, Przemysław Spurek

We construct a general unified framework for learning representation of structured data, i. e. data which cannot be represented as the fixed-length vectors (e. g. sets, graphs, texts or images of varying sizes).

Set Aggregation Network as a Trainable Pooling Layer

1 code implementation3 Oct 2018 Łukasz Maziarka, Marek Śmieja, Aleksandra Nowak, Jacek Tabor, Łukasz Struski, Przemysław Spurek

Global pooling, such as max- or sum-pooling, is one of the key ingredients in deep neural networks used for processing images, texts, graphs and other types of structured data.

Sliced generative models

no code implementations29 Jan 2019 Szymon Knop, Marcin Mazur, Jacek Tabor, Igor Podolak, Przemysław Spurek

In this paper we discuss a class of AutoEncoder based generative models based on one dimensional sliced approach.

Non-linear ICA based on Cramer-Wold metric

no code implementations1 Mar 2019 Przemysław Spurek, Aleksandra Nowak, Jacek Tabor, Łukasz Maziarka, Stanisław Jastrzębski

Non-linear source separation is a challenging open problem with many applications.

Independent Component Analysis based on multiple data-weighting

no code implementations31 May 2019 Andrzej Bedychaj, Przemysław Spurek, Łukasz Struskim, Jacek Tabor

Independent Component Analysis (ICA) - one of the basic tools in data analysis - aims to find a coordinate system in which the components of the data are independent.

Fast and Stable Interval Bounds Propagation for Training Verifiably Robust Models

1 code implementation3 Jun 2019 Paweł Morawiecki, Przemysław Spurek, Marek Śmieja, Jacek Tabor

We present an efficient technique, which allows to train classification networks which are verifiably robust against norm-bounded adversarial attacks.

Spatial Graph Convolutional Networks

2 code implementations11 Sep 2019 Tomasz Danel, Przemysław Spurek, Jacek Tabor, Marek Śmieja, Łukasz Struski, Agnieszka Słowik, Łukasz Maziarka

Graph Convolutional Networks (GCNs) have recently become the primary choice for learning from graph-structured data, superseding hash fingerprints in representing chemical compounds.

Image Classification

WICA: nonlinear weighted ICA

1 code implementation13 Jan 2020 Andrzej Bedychaj, Przemysław Spurek, Aleksandra Nowak, Jacek Tabor

Independent Component Analysis (ICA) aims to find a coordinate system in which the components of the data are independent.

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

LocoGAN -- Locally Convolutional GAN

1 code implementation18 Feb 2020 Łukasz Struski, Szymon Knop, Jacek Tabor, Wiktor Daniec, Przemysław Spurek

In the paper we construct a fully convolutional GAN model: LocoGAN, which latent space is given by noise-like images of possibly different resolutions.

Position

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 Object +1

Adversarial Examples Detection and Analysis with Layer-wise Autoencoders

no code implementations17 Jun 2020 Bartosz Wójcik, Paweł Morawiecki, Marek Śmieja, Tomasz Krzyżek, Przemysław Spurek, Jacek Tabor

We present a mechanism for detecting adversarial examples based on data representations taken from the hidden layers of the target network.

Generative models with kernel distance in data space

1 code implementation15 Sep 2020 Szymon Knop, Marcin Mazur, Przemysław Spurek, Jacek Tabor, Igor Podolak

First, an autoencoder based architecture, using kernel measures, is built to model a manifold of data.

Processing of incomplete images by (graph) convolutional neural networks

no code implementations26 Oct 2020 Tomasz Danel, Marek Śmieja, Łukasz Struski, Przemysław Spurek, Łukasz Maziarka

We investigate the problem of training neural networks from incomplete images without replacing missing values.

Imputation

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 regression

Flow-based SVDD for anomaly detection

no code implementations10 Aug 2021 Marcin Sendera, Marek Śmieja, Łukasz Maziarka, Łukasz Struski, Przemysław Spurek, Jacek Tabor

We propose FlowSVDD -- a flow-based one-class classifier for anomaly/outliers detection that realizes a well-known SVDD principle using deep learning tools.

Anomaly Detection One-class classifier

Efficient GPU implementation of randomized SVD and its applications

no code implementations5 Oct 2021 Łukasz Struski, Paweł Morkisz, Przemysław Spurek, Samuel Rodriguez Bernabeu, Tomasz Trzciński

In this work, we leverage efficient processing operations that can be run in parallel on modern Graphical Processing Units (GPUs), predominant computing architecture used e. g. in deep learning, to reduce the computational burden of computing matrix decompositions.

Data Compression Dimensionality Reduction

HyperCube: Implicit Field Representations of Voxelized 3D Models

1 code implementation12 Oct 2021 Magdalena Proszewska, Marcin Mazur, Tomasz Trzciński, Przemysław Spurek

Recently introduced implicit field representations offer an effective way of generating 3D object shapes.

Continual Learning with Guarantees via Weight Interval Constraints

1 code implementation16 Jun 2022 Maciej Wołczyk, Karol J. Piczak, Bartosz Wójcik, Łukasz Pustelnik, Paweł Morawiecki, Jacek Tabor, Tomasz Trzciński, Przemysław Spurek

We introduce a new training paradigm that enforces interval constraints on neural network parameter space to control forgetting.

Continual Learning

Bounding Evidence and Estimating Log-Likelihood in VAE

no code implementations19 Jun 2022 Łukasz Struski, Marcin Mazur, Paweł Batorski, Przemysław Spurek, Jacek Tabor

Many crucial problems in deep learning and statistics are caused by a variational gap, i. e., a difference between evidence and evidence lower bound (ELBO).

LIDL: Local Intrinsic Dimension Estimation Using Approximate Likelihood

1 code implementation ICLR Workshop GTRL 2021 Piotr Tempczyk, Rafał Michaluk, Łukasz Garncarek, Przemysław Spurek, Jacek Tabor, Adam Goliński

We attempt to address that challenge by proposing a novel approach to the problem: Local Intrinsic Dimension estimation using approximate Likelihood (LIDL).

Density Estimation

Hypernetwork approach to Bayesian MAML

1 code implementation6 Oct 2022 Piotr Borycki, Piotr Kubacki, Marcin Przewięźlikowski, Tomasz Kuśmierczyk, Jacek Tabor, Przemysław Spurek

Unfortunately, previous modifications of MAML are limited due to the simplicity of Gaussian posteriors, MAML-like gradient-based weight updates, or by the same structure enforced for universal and adapted weights.

Few-Shot Learning

HyperSound: Generating Implicit Neural Representations of Audio Signals with Hypernetworks

no code implementations3 Nov 2022 Filip Szatkowski, Karol J. Piczak, Przemysław Spurek, Jacek Tabor, Tomasz Trzciński

Implicit neural representations (INRs) are a rapidly growing research field, which provides alternative ways to represent multimedia signals.

Image Super-Resolution Meta-Learning

HyperNeRFGAN: Hypernetwork approach to 3D NeRF GAN

1 code implementation27 Jan 2023 Adam Kania, Artur Kasymov, Maciej Zięba, Przemysław Spurek

Our architecture produces 2D images, but we use 3D-aware NeRF representation, which forces the model to produce correct 3D objects.

Hypernetworks build Implicit Neural Representations of Sounds

1 code implementation9 Feb 2023 Filip Szatkowski, Karol J. Piczak, Przemysław Spurek, Jacek Tabor, Tomasz Trzciński

Implicit Neural Representations (INRs) are nowadays used to represent multimedia signals across various real-life applications, including image super-resolution, image compression, or 3D rendering.

Image Compression Image Super-Resolution +1

NeRFlame: FLAME-based conditioning of NeRF for 3D face rendering

1 code implementation10 Mar 2023 Wojciech Zając, Joanna Waczyńska, Piotr Borycki, Jacek Tabor, Maciej Zięba, Przemysław Spurek

In contrast to traditional NeRF-based structures that use neural networks for RGB color and volume density modeling, our approach utilizes the FLAME mesh as a distinct density volume.

Gaussian model for closed curves

no code implementations3 Apr 2023 Krzysztof Byrski, Przemysław Spurek, Jacek Tabor

In this work, we propose a density representation of the closed curve, which can be used to detect the complicated templates in the data.

MultiPlaneNeRF: Neural Radiance Field with Non-Trainable Representation

1 code implementation17 May 2023 Dominik Zimny, Artur Kasymov, Adam Kania, Jacek Tabor, Maciej Zięba, Przemysław Spurek

Furthermore, we can train MultiPlaneNeRF on a large data set and force our implicit decoder to generalize across many objects.

Face Identity-Aware Disentanglement in StyleGAN

no code implementations21 Sep 2023 Adrian Suwała, Bartosz Wójcik, Magdalena Proszewska, Jacek Tabor, Przemysław Spurek, Marek Śmieja

Conditional GANs are frequently used for manipulating the attributes of face images, such as expression, hairstyle, pose, or age.

Disentanglement

HyperMask: Adaptive Hypernetwork-based Masks for Continual Learning

1 code implementation29 Sep 2023 Kamil Książek, Przemysław Spurek

In the paper, we propose a method called HyperMask, which trains a single network for all CL tasks.

Continual Learning

Gaussian Splatting with NeRF-based Color and Opacity

1 code implementation21 Dec 2023 Dawid Malarz, Weronika Smolak, Jacek Tabor, Sławomir Tadeja, Przemysław Spurek

To mitigate the caveats of both models, we propose a hybrid model Viewing Direction Gaussian Splatting (VDGS) that uses GS representation of the 3D object's shape and NeRF-based encoding of color and opacity.

HyperPlanes: Hypernetwork Approach to Rapid NeRF Adaptation

1 code implementation2 Feb 2024 Paweł Batorski, Dawid Malarz, Marcin Przewięźlikowski, Marcin Mazur, Sławomir Tadeja, Przemysław Spurek

Neural radiance fields (NeRFs) are a widely accepted standard for synthesizing new 3D object views from a small number of base images.

Few-Shot Learning Object

GaMeS: Mesh-Based Adapting and Modification of Gaussian Splatting

1 code implementation2 Feb 2024 Joanna Waczyńska, Piotr Borycki, Sławomir Tadeja, Jacek Tabor, Przemysław Spurek

In comparison, Gaussian Splatting (GS) is a novel, state-of-the-art technique for rendering points in a 3D scene by approximating their contribution to image pixels through Gaussian distributions, warranting fast training and swift, real-time rendering.

ImplicitDeepfake: Plausible Face-Swapping through Implicit Deepfake Generation using NeRF and Gaussian Splatting

1 code implementation9 Feb 2024 Georgii Stanishevskii, Jakub Steczkiewicz, Tomasz Szczepanik, Sławomir Tadeja, Jacek Tabor, Przemysław Spurek

NeRFs encode the object's shape and color in neural network weights using a handful of images with known camera positions to generate novel views.

Face Swapping

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