Zobrazeno 1 - 10
of 2 990
pro vyhledávání: '"Trzciński, A."'
Continual learning (CL) has emerged as a critical area in machine learning, enabling neural networks to learn from evolving data distributions while mitigating catastrophic forgetting. However, recent research has identified the stability gap -- a ph
Externí odkaz:
http://arxiv.org/abs/2411.04723
Exemplar-Free Class Incremental Learning (EFCIL) tackles the problem of training a model on a sequence of tasks without access to past data. Existing state-of-the-art methods represent classes as Gaussian distributions in the feature extractor's late
Externí odkaz:
http://arxiv.org/abs/2409.18265
Autor:
Grzeszczyk, Michal K., Korzeniowski, Przemysław, Alabed, Samer, Swift, Andrew J., Trzciński, Tomasz, Sitek, Arkadiusz
Right Heart Catheterization is a gold standard procedure for diagnosing Pulmonary Hypertension by measuring mean Pulmonary Artery Pressure (mPAP). It is invasive, costly, time-consuming and carries risks. In this paper, for the first time, we explore
Externí odkaz:
http://arxiv.org/abs/2409.07564
Decoupling lighting from geometry using unconstrained photo collections is notoriously challenging. Solving it would benefit many users, as creating complex 3D assets takes days of manual labor. Many previous works have attempted to address this issu
Externí odkaz:
http://arxiv.org/abs/2408.04474
Autor:
Krzepkowski, Bartłomiej, Michaluk, Monika, Szarwacki, Franciszek, Kubaty, Piotr, Pomponi, Jary, Trzciński, Tomasz, Wójcik, Bartosz, Adamczewski, Kamil
Early exits are an important efficiency mechanism integrated into deep neural networks that allows for the termination of the network's forward pass before processing through all its layers. By allowing early halting of the inference process for less
Externí odkaz:
http://arxiv.org/abs/2407.14320
Test-Time Adaptation (TTA) has recently emerged as a promising strategy for tackling the problem of machine learning model robustness under distribution shifts by adapting the model during inference without access to any labels. Because of task diffi
Externí odkaz:
http://arxiv.org/abs/2407.14231
Autor:
Szczepański, Tomasz, Grzeszczyk, Michal K., Płotka, Szymon, Adamowicz, Arleta, Fudalej, Piotr, Korzeniowski, Przemysław, Trzciński, Tomasz, Sitek, Arkadiusz
Training deep neural networks for 3D segmentation tasks can be challenging, often requiring efficient and effective strategies to improve model performance. In this study, we introduce a novel approach, DeCode, that utilizes label-derived features fo
Externí odkaz:
http://arxiv.org/abs/2407.09437
This paper introduces a continual learning approach named MagMax, which utilizes model merging to enable large pre-trained models to continuously learn from new data without forgetting previously acquired knowledge. Distinct from traditional continua
Externí odkaz:
http://arxiv.org/abs/2407.06322
Autor:
Wysoczańska, Monika, Vobecky, Antonin, Cardiel, Amaia, Trzciński, Tomasz, Marlet, Renaud, Bursuc, Andrei, Siméoni, Oriane
Recent VLMs, pre-trained on large amounts of image-text pairs to align both modalities, have opened the way to open-vocabulary semantic segmentation. Given an arbitrary set of textual queries, image regions are assigned the closest query in feature s
Externí odkaz:
http://arxiv.org/abs/2407.05061
Autor:
Pardyl, Adam, Wronka, Michał, Wołczyk, Maciej, Adamczewski, Kamil, Trzciński, Tomasz, Zieliński, Bartosz
Active Visual Exploration (AVE) is a task that involves dynamically selecting observations (glimpses), which is critical to facilitate comprehension and navigation within an environment. While modern AVE methods have demonstrated impressive performan
Externí odkaz:
http://arxiv.org/abs/2404.03482