Marcin Przewięźlikowski

Marcin Przewięźlikowski

Auto-generated profile, based on publicly available information

Marcin Przewięźlikowski

Jagiellonian University, Faculty of Mathematics and Computer Science

Research Focus & Metrics

Academic Career Length

4Years (2023-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
10 July 2024 in Neurocomputing
Verified
Journal Article
Closed access
MPMarcin Przewięźlikowski
Marcin Przewięźlikowski
PPPrzemysław Przybysz
Przemysław Przybysz
JTJacek Tabor
Jacek Tabor
MZMaciej Zięba
Maciej Zięba
PSPrzemysław Spurek
Przemysław Spurek

9 October 2023 in Neural Networks
Verified
Journal Article
Open access
BWBartosz Wójcik
Bartosz Wójcik
MPMarcin Przewiȩźlikowski
Marcin Przewiȩźlikowski
FSFilip Szatkowski
Filip Szatkowski
MWMaciej Wołczyk
Maciej Wołczyk
KBKlaudia Bałazy
Klaudia Bałazy
Tomasz TrzcinskiTomasz Trzcinski
Tomasz Trzcinski
The problem of reducing processing time of large deep learning models is a fundamental challenge in many real-world applications. Early exit methods strive towards this goal by attaching additional Internal Classifiers (ICs) to intermediate layers of a neural network. ICs can quickly return predictions for easy examples and, as a result, reduce the average inference time of the whole model. However, if a particular IC does not decide to return an answer early, its predictions are discarded, with its computations effectively being wasted. To solve this issue, we introduce Zero Time Waste (ZTW), a novel approach in which each IC reuses predictions returned by its predecessors by (1) adding direct connections between ICs and (2) combining previous outputs in an ensemble-like manner. We conduct extensive experiments across various multiple modes, datasets, and architectures to demonstrate that ZTW achieves a significantly better accuracy vs. inference time trade-off than other early exit methods. On the ImageNet dataset, it obtains superior results over the best baseline method in 11 out of 16 cases, reaching up to 5 percentage points of improvement on low computational budgets.

20 May 2023 in Machine Vision and Applications
Verified
Journal Article
Open access
PDF file
MSMarcin Sendera
Marcin Sendera
MPMarcin Przewiȩźlikowski
Marcin Przewiȩźlikowski
JMJan Miksa
Jan Miksa
MRMateusz Rajski
Mateusz Rajski
KKKonrad Karanowski
Konrad Karanowski
PSPrzemysław Spurek
Przemysław Spurek
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 element represents each class. We propose the general framework for few-shot learning via kernel HyperNetworks—the fusion of kernels and hypernetwork paradigm. Firstly, we introduce the classical realization of this framework, dubbed HyperShot. Compared to reference approaches that apply a gradient-based adjustment of the parameters, our models aim to switch the classification module parameters depending on the task’s embedding. In practice, we utilize a hypernetwork, which takes the aggregated information from support data and returns the classifier’s parameters handcrafted for the considered problem. Moreover, we introduce the kernel-based representation of the support examples delivered to hypernetwork to create the parameters of the classification module. Consequently, we rely on relations between the support examples’ embeddings instead of the backbone models’ direct feature values. Thanks to this approach, our model can adapt to highly different tasks. While such a method obtains very good results, it is limited by typical problems such as poorly quantified uncertainty due to limited data size. We further show that incorporating Bayesian neural networks into our general framework, an approach we call BayesHyperShot, solves this issue.

11 October 2024 in Knowledge-Based Systems
Verified
Journal Article
Open access
MPMarcin Przewięźlikowski
Marcin Przewięźlikowski
MPMateusz Pyla
Mateusz Pyla
BZBartosz Zieliński
Bartosz Zieliński
BTBartłomiej Twardowski
Bartłomiej Twardowski
JTJacek Tabor
Jacek Tabor
MŚMarek Śmieja
Marek Śmieja

17 November 2025 in Knowledge-Based Systems
Verified
Journal Article
Closed access
PBPaweł Batorski
Paweł Batorski
DMDawid Malarz
Dawid Malarz
MPMarcin Przewięźlikowski
Marcin Przewięźlikowski
MMMarcin Mazur
Marcin Mazur
STSławomir K. Tadeja
Sławomir K. Tadeja
PSPrzemysław Spurek
Przemysław Spurek

22 August 2024
Verified
Book Chapter
Closed access
PDF file
MPMarcin Przewięźlikowski
Marcin Przewięźlikowski
MOMarcin Osial
Marcin Osial
BZBartosz Zieliński
Bartosz Zieliński
MŚMarek Śmieja
Marek Śmieja