Zobrazeno 1 - 2
of 2
pro vyhledávání: '"Mikel Menta"'
Autor:
Andrew D. Bagdanov, Luis Herranz, Joost van de Weijer, Xialei Liu, Mikel Menta, Chenshen Wu, Shangling Jui, Bogdan Raducanu
Publikováno v:
CVPR Workshops
Humans are capable of learning new tasks without forgetting previous ones, while neural networks fail due to catastrophic forgetting between new and previously-learned tasks. We consider a class-incremental setting which means that the task-ID is unk
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::d38ea8819507cee2d18cac682f8cd69d
https://doi.org/10.1109/cvprw50498.2020.00121
https://doi.org/10.1109/cvprw50498.2020.00121
Autor:
Marc Masana, Xialei Liu, Bartlomiej Twardowski, Mikel Menta, Andrew D. Bagdanov, Joost van de Weijer
For future learning systems, incremental learning is desirable because it allows for: efficient resource usage by eliminating the need to retrain from scratch at the arrival of new data; reduced memory usage by preventing or limiting the amount of da
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::a3dc0498f3df8ab7405639d04e82f70d
