Zobrazeno 1 - 7
of 7
pro vyhledávání: '"Eden Belouadah"'
Deep learning approaches are successful in a wide range of AI problems and in particular for visual recognition tasks. However, there are still open problems among which is the capacity to handle streams of visual information and the management of cl
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::cb7f0b07921e856edda11b8e41aa4bb5
http://arxiv.org/abs/2202.00386
http://arxiv.org/abs/2202.00386
Autor:
Simone Scardapane, Martin Mundt, Tyler L. Hayes, Simone Calderara, Keiland W. Cooper, Christopher Kanan, Eden Belouadah, Lorenzo Pellegrini, Adrian Popescu, Matthias De Lange, Fabio Cuzzolin, Jeremy Forest, Jary Pomponi, Subutai Ahmad, Qi She, Luca Antiga, Gido M. van de Ven, Davide Maltoni, Davide Bacciu, Vincenzo Lomonaco, Joost van de Weijer, Marc Masana, Antonio Carta, Gabriele Graffieti, Andreas S. Tolias, German Ignacio Parisi, Andrea Cossu, Tinne Tuytelaars
Publikováno v:
CVPR Workshops
Learning continually from non-stationary data streams is a long-standing goal and a challenging problem in machine learning. Recently, we have witnessed a renewed and fast-growing interest in continual learning, especially within the deep learning co
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::d293de3db110ff7791c5e28c4027ea01
http://hdl.handle.net/11573/1612489
http://hdl.handle.net/11573/1612489
Autor:
Adrian Popescu, Eden Belouadah
Publikováno v:
WACV
Incremental learning is useful if an AI agent needs to integrate data from a stream. The problem is non trivial if the agent runs on a limited computational budget and has a bounded memory of past data. In a deep learning approach, the constant compu
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::0705b7dbe8d1ae5d0553472cf77309b9
http://arxiv.org/abs/2001.05755
http://arxiv.org/abs/2001.05755
Publikováno v:
Computer Vision – ECCV 2020 Workshops ISBN: 9783030654139
ECCV Workshops (6)
ECCV Workshops (6)
Incremental Learning (IL) allows AI systems to adapt to streamed data. Most existing algorithms make two strong hypotheses which reduce the realism of the incremental scenario: (1) new data are assumed to be readily annotated when streamed and (2) te
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::5477779b6e53a4d2c94e8d83ba740dee
https://doi.org/10.1007/978-3-030-65414-6_12
https://doi.org/10.1007/978-3-030-65414-6_12
Autor:
Eden Belouadah, Adrian Popescu
Publikováno v:
ICCV
This paper presents a class incremental learning (IL) method which exploits fine tuning and a dual memory to reduce the negative effect of catastrophic forgetting in image recognition. First, we simplify the current fine tuning based approaches which
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::a47bc46ff4d208047cfc5edc637a9edf
https://doi.org/10.1109/iccv.2019.00067
https://doi.org/10.1109/iccv.2019.00067
Autor:
Eden Belouadah, Adrian Popescu
Publikováno v:
Lecture Notes in Computer Science ISBN: 9783030110116
ECCV Workshops (2)
ECCV Workshops (2)
Incremental Learning (IL) is an interesting AI problem when the algorithm is assumed to work on a budget. This is especially true when IL is modeled using a deep learning approach, where two complex challenges arise due to limited memory, which induc
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::e47c98436621669d64345efd33c2f45c
https://doi.org/10.1007/978-3-030-11012-3_11
https://doi.org/10.1007/978-3-030-11012-3_11