Zobrazeno 1 - 10
of 206
pro vyhledávání: '"Araújo, Hélder"'
Group fairness in machine learning is a critical area of research focused on achieving equitable outcomes across different groups defined by sensitive attributes such as race or gender. Federated learning, a decentralized approach to training machine
Externí odkaz:
http://arxiv.org/abs/2410.03855
In the evolving field of machine learning, ensuring fairness has become a critical concern, prompting the development of algorithms designed to mitigate discriminatory outcomes in decision-making processes. However, achieving fairness in the presence
Externí odkaz:
http://arxiv.org/abs/2402.07586
Autor:
Erabati, Gopi Krishna, Araujo, Helder
Inspired by recent advances in vision transformers for object detection, we propose Li3DeTr, an end-to-end LiDAR based 3D Detection Transformer for autonomous driving, that inputs LiDAR point clouds and regresses 3D bounding boxes. The LiDAR local an
Externí odkaz:
http://arxiv.org/abs/2210.15365
Autor:
Erabati, Gopi Krishna, Araujo, Helder
3D object detection is a significant task for autonomous driving. Recently with the progress of vision transformers, the 2D object detection problem is being treated with the set-to-set loss. Inspired by these approaches on 2D object detection and an
Externí odkaz:
http://arxiv.org/abs/2210.15316
Publikováno v:
Computational Science - ICCS 2023. ICCS 2023. Lecture Notes in Computer Science, vol 14073. Springer, Cham
While fairness-aware machine learning algorithms have been receiving increasing attention, the focus has been on centralized machine learning, leaving decentralized methods underexplored. Federated Learning is a decentralized form of machine learning
Externí odkaz:
http://arxiv.org/abs/2209.13678
Autor:
Erabati, Gopi Krishna, Araujo, Helder
Publikováno v:
In Intelligent Systems with Applications June 2024 22
Autor:
Ozyoruk, Kutsev Bengisu, Gokceler, Guliz Irem, Coskun, Gulfize, Incetan, Kagan, Almalioglu, Yasin, Mahmood, Faisal, Curto, Eva, Perdigoto, Luis, Oliveira, Marina, Sahin, Hasan, Araujo, Helder, Alexandrino, Henrique, Durr, Nicholas J., Gilbert, Hunter B., Turan, Mehmet
Deep learning techniques hold promise to develop dense topography reconstruction and pose estimation methods for endoscopic videos. However, currently available datasets do not support effective quantitative benchmarking. In this paper, we introduce
Externí odkaz:
http://arxiv.org/abs/2006.16670
Akademický článek
Tento výsledek nelze pro nepřihlášené uživatele zobrazit.
K zobrazení výsledku je třeba se přihlásit.
K zobrazení výsledku je třeba se přihlásit.
Akademický článek
Tento výsledek nelze pro nepřihlášené uživatele zobrazit.
K zobrazení výsledku je třeba se přihlásit.
K zobrazení výsledku je třeba se přihlásit.