no code implementations • 28 Jan 2024 • Maciej Wielgosz, Stefano Puliti, Binbin Xiang, Konrad Schindler, Rasmus Astrup
In conclusion, this study shows the feasibility of a sensor-agnostic model for diverse lidar data, surpassing sensor-specific approaches and setting new standards in tree segmentation, particularly in complex forests.
no code implementations • 12 Jan 2024 • Muhammad Naveed Riaz, Maciej Wielgosz, Abel Garcia Romera, Antonio M. Lopez
Creating accurate and fast models that predict such intentions from sequential images is challenging.
1 code implementation • 22 Dec 2023 • Binbin Xiang, Maciej Wielgosz, Theodora Kontogianni, Torben Peters, Stefano Puliti, Rasmus Astrup, Konrad Schindler
Detailed forest inventories are critical for sustainable and flexible management of forest resources, to conserve various ecosystem services.
no code implementations • 3 Sep 2023 • Stefano Puliti, Grant Pearse, Peter Surový, Luke Wallace, Markus Hollaus, Maciej Wielgosz, Rasmus Astrup
In conclusion, the FOR-instance dataset contributes to filling a gap in the 3D forest research, enhancing the development and benchmarking of segmentation algorithms for dense airborne laser scanning data.
no code implementations • 11 Aug 2023 • Jan Krupiński, Maciej Wielgosz, Szymon Mazurek, Krystian Strzałka, Paweł Russek, Jakub Caputa, Daria Łukasik, Jakub Grzeszczyk, Michał Karwatowski, Rafał Fraczek, Ernest Jamro, Marcin Pietroń, Sebastian Koryciak, Agnieszka Dąbrowska-Boruch, Kazimierz Wiatr
The research sheds light on the significance of CNN-based IQA in computer-aided cytology diagnosis for animals, enhancing the accuracy of disease classification.
no code implementations • 21 Jul 2023 • Krystian Strzałka, Szymon Mazurek, Maciej Wielgosz, Paweł Russek, Jakub Caputa, Daria Łukasik, Jan Krupiński, Jakub Grzeszczyk, Michał Karwatowski, Rafał Frączek, Ernest Jamro, Marcin Pietroń, Sebastian Koryciak, Agnieszka Dąbrowska-Boruch, Kazimierz Wiatr
This paper explores the innovative use of simulation environments to enhance data acquisition and diagnostics in veterinary medicine, focusing specifically on gait analysis in dogs.
1 code implementation • 27 Jun 2023 • Szymon Mazurek, Maciej Wielgosz
In this paper, we delve into the critical aspect of dataset quality assessment in machine learning classification tasks.
no code implementations • 20 Jun 2023 • Jakub Caputa, Maciej Wielgosz, Daria Łukasik, Paweł Russek, Jakub Grzeszczyk, Michał Karwatowski, Szymon Mazurek, Rafał Frączek, Anna Śmiech, Ernest Jamro, Sebastian Koryciak, Agnieszka Dąbrowska-Boruch, Marcin Pietroń, Kazimierz Wiatr
The primary objective of this research was to enhance the quality of semantic segmentation in cytology images by incorporating super-resolution (SR) architectures.
no code implementations • 7 May 2023 • Jakub Grzeszczyk, Michał Karwatowski, Daria Łukasik, Maciej Wielgosz, Paweł Russek, Szymon Mazurek, Jakub Caputa, Rafał Frączek, Anna Śmiech, Ernest Jamro, Sebastian Koryciak, Agnieszka Dąbrowska-Boruch, Marcin Pietroń, Kazimierz Wiatr
This paper shows the machine learning system which performs instance segmentation of cytological images in veterinary medicine.
no code implementations • 4 May 2023 • Maciej Wielgosz, Stefano Puliti, Phil Wilkes, Rasmus Astrup
We trained a model based on Pointnet++ architecture which achieves 0. 92 F1-score in semantic segmentation.
1 code implementation • 29 Apr 2023 • Maciej Wielgosz, Antonio M. López, Muhammad Naveed Riaz
We present a sample dataset featuring pedestrians generated using the ARCANE framework, a new framework for generating datasets in CARLA (0. 9. 13).
no code implementations • 15 Sep 2021 • Mustafa Sakhai, Maciej Wielgosz
Cybersecurity is essential, and attacks are rapidly growing and getting more challenging to detect.
no code implementations • 12 Feb 2020 • Marcin Pietron, Maciej Wielgosz
Convolutional neural networks (CNN) play a major role in image processing tasks like image classification, object detection, semantic segmentation.
no code implementations • 2 Aug 2019 • Marcin Radzio, Maciej Wielgosz, Matej Mertik
Falls prevention, especially in older people, becomes an increasingly important topic in the times of aging societies.
no code implementations • 28 May 2018 • Krzysztof Wróbel, Marcin Pietroń, Maciej Wielgosz, Michał Karwatowski, Kazimierz Wiatr
The method responsible for mapping compressed network to FPGA and results of this implementation are presented.
1 code implementation • 28 Sep 2017 • Maciej Wielgosz, Matej Mertik, Andrzej Skoczeń, Ernesto De Matteis
In order to conduct the experiments, the authors designed and implemented an adaptive signal quantization algorithm and a custom GRU-based detector and developed a method for the detector parameters selection.
1 code implementation • 20 Jun 2017 • Krzysztof Wróbel, Maciej Wielgosz, Marcin Pietroń, Michał Karwatowski, Aleksander Smywiński-Pohl
This paper presents the analysis of the impact of a floating-point number precision reduction on the quality of text classification.
no code implementations • 2 Feb 2017 • Maciej Wielgosz, Andrzej Skoczeń, Matej Mertik
This paper presents a model based on Deep Learning algorithms of LSTM and GRU for facilitating an anomaly detection in Large Hadron Collider superconducting magnets.
no code implementations • 30 Nov 2016 • Maciej Wielgosz
An external agent-observer monitors a performance of a selected Deep Learning algorithm.
no code implementations • 18 Nov 2016 • Maciej Wielgosz, Andrzej Skoczeń, Matej Mertik
The superconducting LHC magnets are coupled with an electronic monitoring system which records and analyses voltage time series reflecting their performance.
no code implementations • 25 Oct 2016 • Matej Mertik, Maciej Wielgosz, Andrzej Skoczeń
This article presents a development of web application for quench prediction in \gls{te-mpe-ee} at CERN.
no code implementations • 10 Sep 2016 • Maciej Wielgosz, Marcin Pietroń
The authors conducted a series of experiments for various macro parameters of HTM SP, as well as for different levels of video reduction ratios.
no code implementations • 5 Aug 2016 • Maciej Wielgosz, Marcin Pietroń
The classification accuracy of the system was examined through a series of experiments and the performance was given in terms of F1 score as a function of the number of columns, synapses, $min\_overlap$ and $winners\_set\_size$.