Projects funded by the NCN

Information on the principal investigator and host institution

Information of the project and the call

Keywords

Equipment

Delete all

Dynamic Neural Networks for Efficient Machine Learning

2022/45/B/ST6/02817

Keywords:

machine learning deep neural networks conditional computations in neural networks

Descriptors:

  • ST6_011:
  • ST6_007:

Panel:

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

Host institution :

Politechnika Warszawska, Wydział Elektroniki i Technik Informacyjnych

woj. mazowieckie

Other projects carried out by the institution 

Principal investigator (from the host institution):

dr hab. Tomasz Trzciński 

Number of co-investigators in the project: 4

Call: OPUS 23 - announced on 2022-03-28

Amount awarded: 1 261 480 PLN

Project start date (Y-m-d): 2023-01-09

Project end date (Y-m-d): 2027-01-08

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 (2)
  • Articles in post-conference publications (8)
  1. Toward Unsupervised Visual Reasoning: Do Off-the-Shelf Features Know How to Reason?
    Authors:
    Monika Wysoczańska, Tom Monnier, Tomasz Trzciński, David Picard
    Academic press:
    IEEE Access (rok: 2024, tom: 12, strony: 76367-76378), Wydawca: IEEE
    Status:
    Published
    DOI:
    10.1109/ACCESS.2024.3406261 - link to the publication
  2. Zero time waste in pre-trained early exit neural networks
    Authors:
    Bartosz Wójcik, Marcin Przewiȩźlikowski, Filip Szatkowski, Maciej Wołczyk, Klaudia Bałazy, Bartłomiej Krzepkowski, Igor Podolak, Jacek Tabor, Marek Śmieja, Tomasz Trzciński
    Academic press:
    Neural Networks (rok: 2023, tom: 168, strony: 580-601), Wydawca: Elsevier
    Status:
    Published
    DOI:
    10.003 - link to the publication
  1. Adapt Your Teacher: Improving Knowledge Distillation for Exemplar-free Continual Learning
    Authors:
    Filip Szatkowski, Mateusz Pyla, Marcin Przewięźlikowski, Sebastian Cygert, Bartłomiej Twardowski, Tomasz Trzciński
    Conference:
    Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (rok: 2024, tom: Winter Conference on Applications of Computer Vision, strony: 1977-1987), Wydawca: IEEE
    Data:
    konferencja 4.01.2024-8.01.2024
    Status:
    Published
    DOI:
    10.1109/WACV57701.2024.00198 - link to the publication
  2. Hypernetworks Build Implicit Neural Representations of Sounds
    Authors:
    Filip Szatkowski, Karol J. Piczak, Przemysław Spurek, Jacek Tabor & Tomasz Trzciński
    Conference:
    Joint European Conference on Machine Learning and Knowledge Discovery in Databases (rok: 2023, tom: European Conference on Machine Learning and Principles and Practice of Knowledge Discovery in Databases 2023, strony: https://2023.ecmlpkdd.org/), Wydawca: Springer Nature
    Data:
    konferencja 18-22.09.2023
    Status:
    Published
    DOI:
    10.1007/978-3-031-43421-1_39 - link to the publication
  3. Tell Me What Is Good about This Property: Leveraging Reviews for Segment-Personalized Image Collection Summarization
    Authors:
    Monika Wysoczańska,Moran Beladev,Karen Lastmann Assaraf,Fengjun Wang,Ofri Kleinfeld,A. Gil,Hadas Harush Boke
    Conference:
    Proceedings of the 38th AAAI Conference on Artificial Intelligence (rok: 2024, tom: AAAI Conference on Artificial Intelligence, strony: 22983-22989), Wydawca: AAAI OOK-Press
    Data:
    konferencja 20–27.02.2024
    Status:
    Published
    DOI:
    10.1609/aaai.v38i21.30339 - link to the publication
  4. Active Visual Exploration Based on Attention-Map Entropy
    Authors:
    Adam Pardyl, Grzegorz Rypeść, Grzegorz Kurzejamski, Bartosz Zieliński, Tomasz Trzciński.
    Conference:
    Proceedings of the Thirty-Second International Joint Conference on Artificial Intelligence Main Track (rok: 2023, tom: International Joint Conference on Artificial Intelligence, strony: 1303-1311), Wydawca: International Joint Conferences on Artificial Intelligence Organization
    Data:
    konferencja 19th-25th August 2023
    Status:
    Published
    DOI:
    10.24963/ijcai.2023/145 - link to the publication
  5. CLIP-DINOiser: Teaching CLIP a Few DINO Tricks for Open-Vocabulary Semantic Segmentation
    Authors:
    Monika Wysoczańska, Oriane Siméoni, Michaël Ramamonjisoa, Andrei Bursuc , Tomasz Trzciński, Patrick Pérez
    Conference:
    Computer Vision – ECCV 2024, Proceedings, Lecture Notes In Computer Science, (rok: 2024, tom: European Conference on Computer Vision, strony: 320–337), Wydawca: Springer Nature
    Data:
    konferencja 29.09-4.10.2024
    Status:
    Published
    DOI:
    10.1109/WACV57701.2024.00143 - link to the publication
  6. Exploiting Activation Sparsity with Dense to Dynamic-k Mixture-of-Experts Conversion
    Authors:
    Filip Szatkowski, Bartosz Wójcik, Mikołaj Piórczyński, Simone Scardapane
    Conference:
    Advances in Neural Information Processing Systems 37 (NeurIPS 2024) (rok: 2025, tom: Neural Information Processing Systems (NeurIPS) 2024, strony: 43245--43273), Wydawca: Curran Associates, Inc.
    Data:
    konferencja 10.12.2024-15.12.2024
    Status:
    Published
  7. CLIP-DIY: CLIP Dense Inference Yields Open-Vocabulary Semantic Segmentation For-Free
    Authors:
    Monika Wysoczańska, Michaël Ramamonjisoa, Tomasz Trzciński, Oriane Siméoni
    Conference:
    Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV) (rok: 2024, tom: Winter Conference on Applications of Computer Vision (WACV), strony: 1392-1402), Wydawca: IEEE
    Data:
    konferencja 03-08.01.2024
    Status:
    Published
    DOI:
    10.1109/WACV57701.2024.00143 - link to the publication
  8. Sparser, Better, Deeper, Stronger: Improving Static Sparse Training with Exact Orthogonal Initialization
    Authors:
    Aleksandra Nowak, Łukasz Gniecki, Filip Szatkowski, Jacek Tabor
    Conference:
    Proceedings of the 41st International Conference on Machine Learning (rok: 2024, tom: 41st International Conference on Machine Learning (ICML 2024), strony: 38474-38494), Wydawca: PMLP
    Data:
    konferencja 21-27 July 2024
    Status:
    Published

O Narodowym Centrum Nauki

Finansowanie nauki

Współpraca zagraniczna

Centrum prasowe

Deklaracja dostępności
Przetwarzanie danych osobowych
Polityka cookies

Partnerzy