Zobrazeno 1 - 10
of 228
pro vyhledávání: '"Yang, Qinli"'
The dynamic nature of open-world scenarios has attracted more attention to class incremental learning (CIL). However, existing CIL methods typically presume the availability of complete ground-truth labels throughout the training process, an assumpti
Externí odkaz:
http://arxiv.org/abs/2408.10046
Traditional semi-supervised learning tasks assume that both labeled and unlabeled data follow the same class distribution, but the realistic open-world scenarios are of more complexity with unknown novel classes mixed in the unlabeled set. Therefore,
Externí odkaz:
http://arxiv.org/abs/2305.13095
Publikováno v:
In Information Sciences September 2024 679
Publikováno v:
In Information Sciences September 2024 678
Publikováno v:
In Information Sciences September 2024 678
Publikováno v:
In Information Sciences March 2024 661
Publikováno v:
In Journal of Hydrology February 2024 630
Publikováno v:
In Journal of Hydrology: Regional Studies February 2024 51
Publikováno v:
In Journal of Hydrology January 2024 628
Publikováno v:
In Information Processing and Management January 2024 61(1)