Konrad Karanowski
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Konrad Karanowski has a total of 16 co-authors. Here are the top co-authors by number of shared publications:
- Adrian B. Chlopowiec
Department of Artificial Intelligence, Wroclaw University of Science and Technology, Wybrzeże Wyspianskiego 27, 50-370 Wroclaw, Poland
1 shared publication - Jacek Tabor
Faculty of Mathematics and Computer Science, Jagiellonian University, Krakow, Poland
1 shared publication - Jan Kocoń
Wrocław University of Science and Technology
1 shared publication - Jan Miksa
Faculty of Mathematics and Computer Science, Jagiellonian University, Krakow, Poland
1 shared publication - Julita Bielaniewicz
Department of Artificial Intelligence Wrocław University of Science and Technology Poland
1 shared publication - Kamil Kanclerz
Wrocław University of Science and Technology
1 shared publication
Latest Publications
- Open Access
- 20 May 2023
- Published by Springer Nature in Machine Vision and Applications
- Vol. 34 (4) , 1-16
The general framework for few-shot learning by kernel HyperNetworks
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.
- 20 May 2023
- Published by Springer Nature in Machine Vision and Applications
- Vol. 34 (4) , 1-16
Open AccessThe general framework for few-shot learning by kernel HyperNetworks
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.
- Open Access
- 1 January 2023
- Published by Association for Computational Linguistics (ACL)
- p. 13326-13341
PALS: Personalized Active Learning for Subjective Tasks in NLP
Kamil Kanclerz, Konrad Karanowski, Julita Bielaniewicz, Marcin Gruza, Piotr Miłkowski, Jan Kocon, Przemyslaw Kazienko. Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing. 2023.
- 1 January 2023
- Published by Association for Computational Linguistics (ACL)
- p. 13326-13341
Open AccessPALS: Personalized Active Learning for Subjective Tasks in NLP
Kamil Kanclerz, Konrad Karanowski, Julita Bielaniewicz, Marcin Gruza, Piotr Miłkowski, Jan Kocon, Przemyslaw Kazienko. Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing. 2023.
- 21 September 2022
- Published by Springer Nature
- p. 95-105
Data Augmentation for Morphological Analysis of Histopathological Images Using Deep Learning
- 21 September 2022
- Published by Springer Nature
- p. 95-105
Data Augmentation for Morphological Analysis of Histopathological Images Using Deep Learning