1 code implementation • 24 May 2024 • Patryk Krukowski, Anna Bielawska, Kamil Książek, Paweł Wawrzyński, Paweł Batorski, Przemysław Spurek
To address this issue, we introduce HyperInterval, a technique that employs interval arithmetic within the embedding space and utilizes a hypernetwork to map these intervals to the target network parameter space.
1 code implementation • 29 Sep 2023 • Kamil Książek, Przemysław Spurek
In the paper, we propose a method called HyperMask, which dynamically filters a target network depending on the CL task.
no code implementations • 28 Sep 2021 • Kamil Książek, Przemysław Głomb, Michał Romaszewski, Michał Cholewa, Bartosz Grabowski, Krisztián Búza
Neural networks, in particular autoencoders, are one of the most promising solutions for unmixing hyperspectral data, i. e. reconstructing the spectra of observed substances (endmembers) and their relative mixing fractions (abundances), which is needed for effective hyperspectral analysis and classification.
1 code implementation • 21 Jun 2021 • Bartosz Wójcik, Mateusz Żarski, Kamil Książek, Jarosław Adam Miszczak, Mirosław Jan Skibniewski
In recent years, a lot of attention is paid to deep learning methods in the context of vision-based construction site safety systems, especially regarding personal protective equipment.
no code implementations • 4 Nov 2020 • Filip Pałka, Wojciech Książek, Paweł Pławiak, Michał Romaszewski, Kamil Książek
This study is focused on applying genetic algorithms (GA) to model and band selection in hyperspectral image classification.