On the Importance of Attention and Augmentations for Hypothesis Transfer in Domain Adaptation and Generalization

Unsupervised domain adaptation (UDA) aims to mitigate the performance drop due to the distribution shift between the training and testing datasets. UDA methods have achieved performance gains for models trained on a source domain with labeled data to a target domain with only unlabeled data. The sta...

Descripción completa

Detalles Bibliográficos
Autores principales: Sahay, Rajat, Thomas, Georgi, Jahan, Chowdhury Sadman, Manjrekar, Mihir, Popp, Dan, Savakis, Andreas
Formato: Online Artículo Texto
Lenguaje:English
Publicado: MDPI 2023
Materias:
Article
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10611075/
https://www.ncbi.nlm.nih.gov/pubmed/37896503
http://dx.doi.org/10.3390/s23208409

Internet

https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10611075/
https://www.ncbi.nlm.nih.gov/pubmed/37896503
http://dx.doi.org/10.3390/s23208409

Ejemplares similares