Zobrazeno 1 - 1
of 1
pro vyhledávání: '"Dangeti, Vyshnav"'
Autor:
Anand, Deepa, Das, Bipul, Dangeti, Vyshnav, Jerald, Antony, Mullick, Rakesh, Patil, Uday, Sharma, Pakhi, Sudhakar, Prasad
In a setting where segmentation models have to be built for multiple datasets, each with its own corresponding label set, a straightforward way is to learn one model for every dataset and its labels. Alternatively, multi-task architectures with share
Externí odkaz:
http://arxiv.org/abs/2411.11105
