Projects funded by the NCN


Information on the principal investigator and host institution

Information of the project and the call

Keywords

Equipment

Delete all

Hypernetworks methods in Meta-Learning

2021/43/B/ST6/01456

Keywords:

Meta learning deep learning continual learning few-shot learning Hypernetworks

Descriptors:

  • ST6_007:

Panel:

ST6 - Computer science and informatics: informatics and information systems, computer science, scientific computing, intelligent systems

Host institution :

Uniwersytet Jagielloński, Wydział Matematyki i Informatyki

woj. małopolskie

Other projects carried out by the institution 

Principal investigator (from the host institution):

dr Przemysław Ernest Spurek 

Number of co-investigators in the project: 7

Call: OPUS 22 - announced on 2021-09-15

Amount awarded: 1 299 546 PLN

Project start date (Y-m-d): 2022-07-04

Project end date (Y-m-d): 2026-07-03

Project duration:: 48 months (the same as in the proposal)

Project status: Pending project

Project description

Download the project description in a pdf file

Note - project descriptions were prepared by the authors of the applications themselves and placed in the system in an unchanged form.

Information in the final report

  • Publication in academic press/journals (1)
  • Articles in post-conference publications (4)
  1. The general framework for few-shot learning by kernel HyperNetworks
    Authors:
    Marcin Sendera, Marcin Przewięźlikowski, Jan Miksa, Mateusz Rajski, Konrad Karanowski, Maciej Zięba, Jacek Tabor, Przemysław Spurek
    Academic press:
    Machine Vision and Applications (), Wydawca: Springer
    Status:
    Published
    DOI:
    10.1007/s00138-023-01403-4 - link to the publication
  1. Hypernetworks Build Implicit Neural Representations of Sounds
    Authors:
    Filip Szatkowski, Karol J. Piczak, Przemysław Spurek, Jacek Tabor, Tomasz Trzciński
    Conference:
    Machine Learning and Knowledge Discovery in Databases: Research Track: European Conference, ECML PKDD 2023 (tom: European Conference, ECML PKDD 2023, strony: 661–676), Wydawca: Springer-Verlag
    Data:
    konferencja 18–22.09.2023
    Status:
    Published
    DOI:
    10.1007/978-3-031-43421-1_39 - link to the publication
  2. Bounding Evidence and Estimating Log-Likelihood in VAE
    Authors:
    Łukasz Struski, Marcin Mazur, Paweł Batorski, Przemysław Spurek, Jacek Tabor
    Conference:
    Proceedings of The 26th International Conference on Artificial Intelligence and Statistics AISTATS (tom: 26th International Conference on Artificial Intelligence and Statistics AISTATS, strony: 5036--5051), Wydawca: PMLR
    Data:
    konferencja 25--27.04.2023
    Status:
    Published
    DOI:
    10.48550/arXiv.2206.09453 - link to the publication
  3. Face Identity-Aware Disentanglement in StyleGAN
    Authors:
    Adrian Suwała, Bartosz Wojcik, Magdalena Proszewska, Jacek Tabor, Przemysław Spurek, Marek Smieja
    Conference:
    Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV) (tom: IEEE/CVF Winter Conference on Applications of Computer Vision (WACV), strony: 5222-5231), Wydawca: IEEE
    Data:
    konferencja 02-07 January 2024
    Status:
    Published
    DOI:
    10.48550/arXiv.2309.12033 - link to the publication
  4. HyperShot: Few-Shot Learning by Kernel HyperNetworks
    Authors:
    Marcin Sendera, Marcin Przewięźlikowski, Konrad Karanowski, Maciej Zięba, Jacek Tabor, Przemysław Spurek
    Conference:
    2023 IEEE/CVF Winter Conference on Applications of Computer Vision (WACV) (tom: IEEE/CVF Winter Conference on Applications of Computer Vision (WACV), strony: 2468-2477), Wydawca: IEEE
    Data:
    konferencja 02-07 January 2023
    Status:
    Published
    DOI:
    10.1109/WACV56688.2023.00250 - link to the publication