1 code implementation • 4 Apr 2024 • Adam Pardyl, Michał Wronka, Maciej Wołczyk, Kamil Adamczewski, Tomasz Trzciński, Bartosz Zieliński
Active Visual Exploration (AVE) is a task that involves dynamically selecting observations (glimpses), which is critical to facilitate comprehension and navigation within an environment.
no code implementations • 12 Mar 2024 • Filip Szatkowski, Fei Yang, Bartłomiej Twardowski, Tomasz Trzciński, Joost Van de Weijer
We assess the accuracy and computational cost of various continual learning techniques enhanced with early-exits and TLC across standard class-incremental learning benchmarks such as 10 split CIFAR100 and ImageNetSubset and show that TLC can achieve the accuracy of the standard methods using less than 70\% of their computations.
1 code implementation • 6 Mar 2024 • Bartosz Cywiński, Kamil Deja, Tomasz Trzciński, Bartłomiej Twardowski, Łukasz Kuciński
We introduce GUIDE, a novel continual learning approach that directs diffusion models to rehearse samples at risk of being forgotten.
no code implementations • 1 Mar 2024 • Michal Nauman, Michał Bortkiewicz, Mateusz Ostaszewski, Piotr Miłoś, Tomasz Trzciński, Marek Cygan
We tested these agents across 14 diverse tasks from 2 simulation benchmarks.
1 code implementation • 18 Jan 2024 • Grzegorz Rypeść, Sebastian Cygert, Valeriya Khan, Tomasz Trzciński, Bartosz Zieliński, Bartłomiej Twardowski
Class-incremental learning is becoming more popular as it helps models widen their applicability while not forgetting what they already know.
1 code implementation • 10 Jan 2024 • Michal K. Grzeszczyk, Tomasz Trzciński, Arkadiusz Sitek
In this work, we present a novel, machine-learning approach for constructing Multiclass Interpretable Scoring Systems (MISS) - a fully data-driven methodology for generating single, sparse, and user-friendly scoring systems for multiclass classification problems.
1 code implementation • 27 Dec 2023 • Sebastian Dziadzio, Çağatay Yıldız, Gido M. van de Ven, Tomasz Trzciński, Tinne Tuytelaars, Matthias Bethge
In a simple setting with direct supervision on the generative factors, we show how learning class-agnostic transformations offers a way to circumvent catastrophic forgetting and improve classification accuracy over time.
1 code implementation • 21 Dec 2023 • Kamil Deja, Bartosz Cywiński, Jan Rybarczyk, Tomasz Trzciński
In this work, we introduce Adapt & Align, a method for continual learning of neural networks by aligning latent representations in generative models.
1 code implementation • 19 Dec 2023 • Monika Wysoczańska, Oriane Siméoni, Michaël Ramamonjisoa, Andrei Bursuc, Tomasz Trzciński, Patrick Pérez
We propose to locally improve dense MaskCLIP features, which are computed with a simple modification of CLIP's last pooling layer, by integrating localization priors extracted from self-supervised features.
no code implementations • 22 Nov 2023 • Daniel Marczak, Sebastian Cygert, Tomasz Trzciński, Bartłomiej Twardowski
In the field of continual learning, models are designed to learn tasks one after the other.
no code implementations • 30 Oct 2023 • Wojciech Masarczyk, Tomasz Trzciński, Mateusz Ostaszewski
In the era of transfer learning, training neural networks from scratch is becoming obsolete.
1 code implementation • 27 Oct 2023 • Michal K. Grzeszczyk, Szymon Płotka, Beata Rebizant, Katarzyna Kosińska-Kaczyńska, Michał Lipa, Robert Brawura-Biskupski-Samaha, Przemysław Korzeniowski, Tomasz Trzciński, Arkadiusz Sitek
In this paper, we introduce TabAttention, a novel module that enhances the performance of Convolutional Neural Networks (CNNs) with an attention mechanism that is trained conditionally on tabular data.
no code implementations • 18 Oct 2023 • Mateusz Pyla, Kamil Deja, Bartłomiej Twardowski, Tomasz Trzciński
Bayesian Flow Networks (BFNs) has been recently proposed as one of the most promising direction to universal generative modelling, having ability to learn any of the data type.
1 code implementation • 25 Sep 2023 • Monika Wysoczańska, Michaël Ramamonjisoa, Tomasz Trzciński, Oriane Siméoni
The emergence of CLIP has opened the way for open-world image perception.
no code implementations • 23 Sep 2023 • Adam Pardyl, Grzegorz Kurzejamski, Jan Olszewski, Tomasz Trzciński, Bartosz Zieliński
Vision transformers have excelled in various computer vision tasks but mostly rely on rigid input sampling using a fixed-size grid of patches.
1 code implementation • 18 Sep 2023 • Valeriya Khan, Sebastian Cygert, Kamil Deja, Tomasz Trzciński, Bartłomiej Twardowski
We notice that in VAE-based generative replay, this could be attributed to the fact that the generated features are far from the original ones when mapped to the latent space.
no code implementations • 18 Sep 2023 • Damian Sójka, Sebastian Cygert, Bartłomiej Twardowski, Tomasz Trzciński
Test-time adaptation is a promising research direction that allows the source model to adapt itself to changes in data distribution without any supervision.
no code implementations • 23 Aug 2023 • Daniel Marczak, Grzegorz Rypeść, Sebastian Cygert, Tomasz Trzciński, Bartłomiej Twardowski
However, these settings are not well aligned with real-life scenarios, where a learning agent has access to a vast amount of unlabeled data encompassing both novel (entirely unlabeled) classes and examples from known classes.
1 code implementation • 18 Aug 2023 • Filip Szatkowski, Mateusz Pyla, Marcin Przewięźlikowski, Sebastian Cygert, Bartłomiej Twardowski, Tomasz Trzciński
In this work, we investigate exemplar-free class incremental learning (CIL) with knowledge distillation (KD) as a regularization strategy, aiming to prevent forgetting.
no code implementations • 23 Jun 2023 • Jan Dubiński, Kamil Deja, Sandro Wenzel, Przemysław Rokita, Tomasz Trzciński
In particular, we examine the performance of variational autoencoders and generative adversarial networks, expanding the GAN architecture by an additional regularisation network and a simple, yet effective postprocessing step.
no code implementations • 22 Jun 2023 • Jan Dubiński, Antoni Kowalczuk, Stanisław Pawlak, Przemysław Rokita, Tomasz Trzciński, Paweł Morawiecki
In this paper, we examine whether it is possible to determine if a specific image was used in the training set, a problem known in the cybersecurity community and referred to as a membership inference attack.
no code implementations • CVPR 2023 • Kacper Kania, Stephan J. Garbin, Andrea Tagliasacchi, Virginia Estellers, Kwang Moo Yi, Julien Valentin, Tomasz Trzciński, Marek Kowalski
Generating faithful visualizations of human faces requires capturing both coarse and fine-level details of the face geometry and appearance.
no code implementations • 27 Mar 2023 • Michał Zając, Kamil Deja, Anna Kuzina, Jakub M. Tomczak, Tomasz Trzciński, Florian Shkurti, Piotr Miłoś
Diffusion models have achieved remarkable success in generating high-quality images thanks to their novel training procedures applied to unprecedented amounts of data.
1 code implementation • 11 Mar 2023 • Adam Pardyl, Grzegorz Rypeść, Grzegorz Kurzejamski, Bartosz Zieliński, Tomasz Trzciński
Active visual exploration addresses the issue of limited sensor capabilities in real-world scenarios, where successive observations are actively chosen based on the environment.
1 code implementation • 9 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.
no code implementations • 7 Feb 2023 • Michal K. Grzeszczyk, Paulina Adamczyk, Sylwia Marek, Ryszard Pręcikowski, Maciej Kuś, M. Patrycja Lelujko, Rosmary Blanco, Tomasz Trzciński, Arkadiusz Sitek, Maciej Malawski, Aneta Lisowska
The effectiveness of digital treatments can be measured by requiring patients to self-report their state through applications, however, it can be overwhelming and causes disengagement.
no code implementations • 20 Dec 2022 • Monika Wysoczańska, Tom Monnier, Tomasz Trzciński, David Picard
Recent advances in visual representation learning allowed to build an abundance of powerful off-the-shelf features that are ready-to-use for numerous downstream tasks.
no code implementations • 11 Nov 2022 • Michał Bortkiewicz, Jakub Łyskawa, Paweł Wawrzyński, Mateusz Ostaszewski, Artur Grudkowski, Tomasz Trzciński
In this paper, we address this gap in the state-of-the-art approaches and propose a method in which the validity of higher-level actions (thus lower-level goals) is constantly verified at the higher level.
Hierarchical Reinforcement Learning reinforcement-learning +1
no code implementations • 3 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.
no code implementations • 4 Jul 2022 • Jan Dubiński, Kamil Deja, Sandro Wenzel, Przemysław Rokita, Tomasz Trzciński
Especially prone to mode collapse are conditional GANs, which tend to ignore the input noise vector and focus on the conditional information.
no code implementations • 4 Jul 2022 • Stanisław Pawlak, Filip Szatkowski, Michał Bortkiewicz, Jan Dubiński, Tomasz Trzciński
We introduce a new method for internal replay that modulates the frequency of rehearsal based on the depth of the network.
1 code implementation • 16 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.
1 code implementation • 31 May 2022 • Kamil Deja, Anna Kuzina, Tomasz Trzciński, Jakub M. Tomczak
Their main strength comes from their unique setup in which a model (the backward diffusion process) is trained to reverse the forward diffusion process, which gradually adds noise to the input signal.
1 code implementation • 27 May 2022 • Szymon Płotka, Adam Klasa, Aneta Lisowska, Joanna Seliga-Siwecka, Michał Lipa, Tomasz Trzciński, Arkadiusz Sitek
We found that automated fetal biometric measurements obtained by FUVAI were comparable to the measurements performed by experienced sonographers The observed differences in measurement values were within the range of inter- and intra-observer variability.
1 code implementation • 19 May 2022 • Szymon Płotka, Michal K. Grzeszczyk, Robert Brawura-Biskupski-Samaha, Paweł Gutaj, Michał Lipa, Tomasz Trzciński, Arkadiusz Sitek
Predicting fetal weight at birth is an important aspect of perinatal care, particularly in the context of antenatal management, which includes the planned timing and the mode of delivery.
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 • 23 Jan 2022 • Tomasz Szczepański, Arkadiusz Sitek, Tomasz Trzciński, Szymon Płotka
We show that our proposed method is more robust than previous attempts to counter confounding factors such as ECG leads in chest X-rays that often influence model classification decisions.
no code implementations • 17 Jan 2022 • Wojciech Masarczyk, Paweł Wawrzyński, Daniel Marczak, Kamil Deja, Tomasz Trzciński
Our approach leverages allocation of past data in a~set of generative models such that most of them do not require retraining after a~task.
1 code implementation • CVPR 2022 • Kacper Kania, Kwang Moo Yi, Marek Kowalski, Tomasz Trzciński, Andrea Tagliasacchi
We extend neural 3D representations to allow for intuitive and interpretable user control beyond novel view rendering (i. e. camera control).
1 code implementation • NeurIPS 2021 • Marcin Sendera, Jacek Tabor, Aleksandra Nowak, Andrzej Bedychaj, Massimiliano Patacchiola, Tomasz Trzciński, Przemysław Spurek, Maciej Zięba
This makes the GP posterior locally non-Gaussian, therefore we name our method Non-Gaussian Gaussian Processes (NGGPs).
1 code implementation • 12 Oct 2021 • Magdalena Proszewska, Marcin Mazur, Tomasz Trzciński, Przemysław Spurek
Recently introduced implicit field representations offer an effective way of generating 3D object shapes.
no code implementations • 5 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.
no code implementations • 4 Sep 2021 • Wojciech Masarczyk, Kamil Deja, Tomasz Trzciński
Catastrophic forgetting of previously learned knowledge while learning new tasks is a widely observed limitation of contemporary neural networks.
1 code implementation • 3 Aug 2021 • Ivan Kostiuk, Przemysław Stachura, Sławomir K. Tadeja, Tomasz Trzciński, Przemysław Spurek
In such a case, we have to ``understand'' the object's composition and coloring scheme of each part.
1 code implementation • 14 Jul 2021 • Szymon Płotka, Tomasz Włodarczyk, Adam Klasa, Michał Lipa, Arkadiusz Sitek, Tomasz Trzciński
The main goal in fetal ultrasound scan video analysis is to find proper standard planes to measure the fetal head, abdomen and femur.
1 code implementation • 23 Jun 2021 • Kamil Deja, Paweł Wawrzyński, Wojciech Masarczyk, Daniel Marczak, Tomasz Trzciński
We propose a new method for unsupervised generative continual learning through realignment of Variational Autoencoder's latent space.
1 code implementation • 21 Jun 2021 • Witold Oleszkiewicz, Dominika Basaj, Igor Sieradzki, Michał Górszczak, Barbara Rychalska, Koryna Lewandowska, Tomasz Trzciński, Bartosz Zieliński
Motivated by this observation, we introduce a novel visual probing framework for explaining the self-supervised models by leveraging probing tasks employed previously in natural language processing.
1 code implementation • NeurIPS 2021 • Maciej Wołczyk, Bartosz Wójcik, Klaudia Bałazy, Igor Podolak, Jacek Tabor, Marek Śmieja, Tomasz Trzciński
The problem of reducing processing time of large deep learning models is a fundamental challenge in many real-world applications.
no code implementations • 18 Apr 2021 • Szymon Płotka, Tomasz Włodarczyk, Ryszard Szczerba, Przemysław Rokita, Patrycja Bartkowska, Oskar Komisarek, Artur Matthews-Brzozowski, Tomasz Trzciński
Convolutional neural networks (CNNs) are used in many areas of computer vision, such as object tracking and recognition, security, military, and biomedical image analysis.
no code implementations • 1 Apr 2021 • Kacper Kania, Marek Kowalski, Tomasz Trzciński
The creation of plausible and controllable 3D human motion animations is a long-standing problem that requires a manual intervention of skilled artists.
1 code implementation • 11 Feb 2021 • Przemysław Spurek, Sebastian Winczowski, Maciej Zięba, Tomasz Trzciński, Kacper Kania, Marcin Mazur
This way, we can sample a mesh quad on that sphere and project it back onto the object's manifold.
1 code implementation • 11 Feb 2021 • Przemysław Spurek, Artur Kasymov, Marcin Mazur, Diana Janik, Sławomir Tadeja, Łukasz Struski, Jacek Tabor, Tomasz Trzciński
In this work, we reformulate the problem of point cloud completion into an object hallucination task.
1 code implementation • 25 Nov 2020 • Kamil Deja, Paweł Wawrzyński, Daniel Marczak, Wojciech Masarczyk, Tomasz Trzciński
We introduce a binary latent space autoencoder architecture to rehearse training samples for the continual learning of neural networks.
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.
no code implementations • 16 Aug 2020 • Tomasz Włodarczyk, Szymon Płotka, Przemysław Rokita, Nicole Sochacki-Wójcicka, Jakub Wójcicki, Michał Lipa, Tomasz Trzciński
Based on the conducted results and model efficiency, we decided to extend U-Net by adding a parallel branch for classification task.
1 code implementation • 15 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.
1 code implementation • 11 Jun 2020 • Kamil Deja, Jan Dubiński, Piotr Nowak, Sandro Wenzel, Tomasz Trzciński
To address these shortcomings, we introduce a novel method dubbed end-to-end Sinkhorn Autoencoder, that leverages sinkhorn algorithm to explicitly align distribution of encoded real data examples and generated noise.
no code implementations • 23 Mar 2020 • Witold Oleszkiewicz, Taro Makino, Stanisław Jastrzębski, Tomasz Trzciński, Linda Moy, Kyunghyun Cho, Laura Heacock, Krzysztof J. Geras
Deep neural networks (DNNs) show promise in breast cancer screening, but their robustness to input perturbations must be better understood before they can be clinically implemented.
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.
no code implementations • 24 Aug 2019 • Tomasz Włodarczyk, Szymon Płotka, Tomasz Trzciński, Przemysław Rokita, Nicole Sochacki-Wójcicka, Michał Lipa, Jakub Wójcicki
To achieve this goal, we propose to first use a deep neural network architecture for segmenting prenatal ultrasound images and then automatically extract two biophysical ultrasound markers, cervical length (CL) and anterior cervical angle (ACA), from the resulting images.
1 code implementation • 9 Dec 2018 • Maciej Pęśko, Adam Svystun, Paweł Andruszkiewicz, Przemysław Rokita, Tomasz Trzciński
In this paper, we propose a solution to transform a video into a comics.
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.
no code implementations • 5 Sep 2018 • Maciej Pęśko, Tomasz Trzciński
The work by Gatys et al. [1] recently showed a neural style algorithm that can produce an image in the style of another image.
no code implementations • 9 Aug 2017 • Pawel Cyrta, Tomasz Trzciński, Wojciech Stokowiec
In this paper we propose a new method of speaker diarization that employs a deep learning architecture to learn speaker embeddings.
1 code implementation • 21 Jul 2017 • Ivona Tautkute, Aleksandra Możejko, Wojciech Stokowiec, Tomasz Trzciński, Łukasz Brocki, Krzysztof Marasek
In this paper, we propose a multi-modal search engine for interior design that combines visual and textual queries.