Haku
Viitteet 1-2 / 2
Incremental Multi-Domain Learning with Domain-Specific Early Exits
(2020)
Diplomityö
Diplomityö
Deep learning architectures can achieve state-of-the-art results in several computer vision tasks. However, these methods are highly specialized, i.e., for every task from a new domain, an independent new model is required. ...
Unsupervised Domain Adaptation for Audio Classification
(2020)
Pro gradu -tutkielma
Pro gradu -tutkielma
Machine learning algorithms have achieved the state-of-the-art results by utilizing deep neural networks (DNNs) across different tasks in recent years. However, the performance of DNNs suffers from mismatched conditions ...